Tools, Techniques, and Applications of Data Visualization in Education and Machine Learning

Tools, Techniques, and Applications of Data Visualization in Education and Machine Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review Tools, Techniques, and Applications of Data Visualization in Education and Machine Learning Maselesele Jacob, Magara P. Tshedza, Mukwevho Hulisani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7560670/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Data visualization (DV) and learning analytics (LA) play a critical role in simplifying complexity, enhancing interpretation, and supporting evidence-based decision-making across educational, business, healthcare, and policy domains. Despite the rapid growth of research between 2015–2025, gaps remain in methodological transparency, tool adoption, and balanced reporting of advanced visualization techniques. This review systematically examines DV and LA literature to (i) assess trends in publication outputs and geographical contributions, (ii) identify the most frequently applied databases, tools, and visualization techniques, (iii) analyze decision-making outcomes and cognitive load implications, (iv) map target user groups, and (v) highlight persistent challenges and limitations constraining the field. A systematic search of Google Scholar, Scopus, and Web of Science yielded 101,685 initial records. After duplicate removal and screening, 123 studies were included for full analysis. Studies were classified into categories of visualization tools, techniques, application domains, and decision-making outcomes. Descriptive statistics and thematic synthesis were applied, and results are reported with visual summaries. Research outputs show steady growth with peaks in 2021–2024, dominated by journal articles (69.92%) and contributions from the United States (24.39%), China (18.70%), and India (10.57%). The most frequently used databases were Google Scholar (52.03%), Scopus (30.08%), and Web of Science (17.89%). Tool distribution highlighted the dominance of Tableau (44.72%), Power BI (14.63%), and Excel (8.94%), while dashboards (26.83%), bar graphs (16.26%), and line graphs (12.20%) were the most reported visualization techniques. Education (43.09%) and business (39.84%) emerged as the leading domains of application, with decision-making outcomes most often improving business/industry performance (30%) and policy or healthcare (15% each). Cognitive load findings revealed a balance between reduction strategies (25%) and risks of complexity (20%), underscoring design trade-offs. User groups were led by analysts (32.52%), managers (19.51%), and researchers/students (17.07% each). Key limitations included complexity and scalability (20%), interpretability issues (18%), and data integration challenges (15%). The evidence demonstrates that DV and LA provide significant pedagogical, operational, and strategic benefits. However, reliance on dashboards and descriptive methods reflects underutilization of advanced predictive or interactive approaches. Addressing methodological transparency, scalability, and user training will be essential for broader adoption. A framework (Fig. 18) is proposed to integrate inputs, context, methods, mechanisms, users, and boundaries, offering a structured path toward advancing the role of DV and LA in educational decision-making. Educational Philosophy and Theory Educational Psychology Special Education Artificial Intelligence and Machine Learning data visualization learning analytics decision-making dashboards systematic review education business intelligence cognitive load Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 Figure 15 Figure 16 Figure 17 1. Introduction In today’s data-driven environment, the integration of visualization and analytical tools has profoundly transformed organizational and educational practices by enabling the interpretation of complex datasets, the extraction of actionable insights, and the support of informed decision-making, ultimately fostering innovation and competitive advantage.In the context of education and learning, visualization techniques have become essential in transforming raw educational data into meaningful insights, enabling educators and learners to make evidence-based decisions that enhance both teaching practices and learning outcomes (Buenaño-Fernandez et al., 2019 ; Paiva et al., 2019; Järvelä et al., 2017). Recent studies highlight the transformative impact of data visualization and mining techniques across diverse domains, with applications ranging from optimizing educational processes and supporting pedagogical decision-making to enhancing learners’ self-regulation and engagement in technology-enhanced environments (Järvelä et al., 2017; Paiva et al., 2019). Recent research highlights the transformative impact of data visualization and data mining techniques across educational and learning contexts. Visualization tools have been instrumental in supporting educators and learners to interpret complex datasets, monitor performance, and make evidence-based decisions that enhance learning outcomes (Bergram & Ochan, 2018 ). Despite these advancements, there remains a gap in understanding the comprehensive application of these technologies within resource-constrained learning environments or emerging educational systems (Paiva et al.2019). Smaller institutions and programs, which often face limitations in data infrastructure and analytic expertise, require tailored approaches to leverage visualization and mining techniques effectively for decision-making. However, most existing literature has focused on well-resourced or large-scale educational settings, leaving smaller contexts underexplored (Anderson, 2019 ). Recent research emphasizes the transformative role of data visualization and data mining in enhancing decision-making across educational and learning contexts. Visualization tools have been applied to support learners’ self-regulation, improve comprehension of complex datasets, and guide evidence-based pedagogical decisions (Järvelä et al., 2017; Paiva et al., 2019; Krist, 2019; Milligan, 2019 ). Data mining techniques have been explored for their ability to extract actionable insights from educational data, such as predicting student performance, identifying knowledge gaps, and informing curriculum design (Buenaño-Fernandez et al., 2019 ; Anderson, 2019 ; Murumba et al., 2023). Despite these developments, a gap remains in understanding how these technologies function comprehensively in resource-constrained or emerging educational settings, particularly with smaller institutions and programs that face limitations in analytics expertise (Paiva et al., 2019; Perdana et al., 2023; Milligan, 2019 ). Most studies have focused on well-resourced or large-scale learning environments, leaving underexplored contexts without guidance on effective implementation of visualization and mining tools for decision-making (Krist, 2019; Anderson, 2019 ; Järvelä et al., 2017). The increasing complexity of educational environments and the rapid evolution of learning technologies have highlighted the need for effective data-driven decision-making to improve learning outcomes (Buenaño-Fernandez et al., 2019 ; Järvelä et al., 2017; Paiva et al., 2019). Research has examined various approaches for applying data visualization and mining techniques in education, including the use of interactive dashboards, learning analytics platforms, and advanced visualization tools to support both teachers and learners in monitoring progress and guiding instructional strategies (Janssen & Helbig, 2017). Despite these advances, challenges remain in fully integrating these technologies, particularly in resource-constrained or emerging educational settings where expertise and infrastructure may be limited (Perdana et al., 2023; Anderson, 2019 ). Prior studies have explored the design, implementation, and evaluation of visual analytics systems across diverse learning contexts, highlighting both successful applications and persistent barriers to adoption (Järvelä et al., 2017; Paiva et al., 2019; Milligan, 2019 ). This systematic review seeks to synthesize a decade of research on data visualization and learning analytics, identifying key trends, challenges, and opportunities associated with these technologies. By analyzing studies published over this period, the review aims to provide actionable insights for educators, instructional designers, and policymakers, ultimately enhancing evidence-based decision-making and learning outcomes. Table 1 presents a comparative analysis of existing review works and the focus of this study, emphasizing its distinct contribution in exploring the applications and impact of data visualization and mining techniques in educational contexts. Uncovering patterns in technological adoption, showcasing effective case studies, and discussing practical implications, this review aims to establish a foundation for future research and informed educational practice (Murumba et al., 2023). Table 1 Comparative Analysis of Existing Review Works and the Proposed Systematic Review on the Applications and Impact of Data Visualization and Learning Analytics on Educational Decision-Making. Ref. Contribution Pros Cons Perdana, A., Robb, A., & et al. (2021). Explores interactive data visualization techniques for enhancing decision-making in education. Demonstrates how interactive visualizations improve comprehension and engagement. Limited focus on real-time or adaptive learning environments. Milligan, J. N. (2019) Demonstrates practical use of Tableau for visualizing educational data to support decision-making. Provides hands-on guidance for educators and analysts; practical tool implementation. Focused mainly on Tableau; less coverage of other visualization platforms. Krist, B. (2018). Investigates foundational visualization techniques for interpreting complex educational datasets. Simple, clear methods that improve data literacy and interpretation. Limited empirical evaluation in educational contexts. Paiva, A., et al. (2020). Examine educators’ perceptions of different visualization tools for teaching decisions. Highlights teacher preferences and practical applicability. Sample size and regional focus may limit generalization. Murumba, J., et al. (2022). Reviews learning analytics dashboards and visualization frameworks in digital learning environments. Comprehensive coverage of visualization dashboards and educational insights. Limited focus on small-scale classroom adoption. Anderson, T. (2019). Shows practical integration of personal analytics and visualizations for educational decision-making. Clear framework for educators and students to leverage data for learning improvements. Focused on individual projects; less about institutional-wide implementation. Chatti, M. A., Muslim, A., & Thüs, H. (2012) Introduces a comprehensive reference model for learning analytics. Provides a structured framework for understanding learning analytics. Lacks empirical validation; theoretical in nature. Ferguson, R. ( 2012 ). Discusses the drivers, developments, and challenges in learning analytics. Offers insights into the evolving landscape of learning analytics. Limited focus on practical applications; more theoretical. Siemens, G., & Long, P. (2011). Explores the role of analytics in learning and education Highlights the potential of analytics in enhancing educational outcomes. Brief overview; lacks in-depth analysis. Romero, C., & Ventura, S. (2010). Reviews the state of the art in educational data visualization. Provides a comprehensive overview of educational data visualization techniques. Focuses primarily on data tools; less on visualization. Paiva, A., et al. (2020) Investigates teachers' perceptions of data visualization tools. Offers practical insights into educators' views on data visualization. Limited sample size; region-specific findings. Williamson, W. ( 2022 ). 2024 Reviews research on learning analytics dashboards in higher education Provides a comprehensive analysis of dashboard research. Focuses mainly on higher education; less on K-12 Proposed systematic review Synthesizes studies (2015–2025) on data visualization and learning analytics in education Comprehensive: covers visualization types, analytic methods, teacher/student perspectives, and learning outcomes. Limited by exclusion of gray literature and non-English studies. Despite the growing body of research on DV and LA, several gaps remain that limit their effective application in education and machine learning. Most existing reviews emphasize higher education, while K–12 and small-scale classroom environments remain underexplored. This gap overlooks unique challenges such as limited infrastructure, teacher training needs, and resource constraints, which are critical for equitable adoption of visualization and analytics. Many studies focus either on visualization tools and techniques or on learning analytics frameworks, but rarely on their integrated impact. As a result, there is insufficient understanding of how DV and LA together can enhance pedagogy, institutional decision-making, and student outcomes. The majority of prior work relies on short-term, cross-sectional data, which restricts insight into the long-term effects of visualization and analytics on teaching quality and institutional performance. Few studies employ longitudinal or mixed-method approaches that can capture evolving adoption patterns and sustained impact. While technical efficiency and tool implementation are well-studied, less attention is given to teacher engagement, institutional culture, and decision-making processes that shape adoption. These factors are crucial for bridging the gap between technical capacity and practical educational impact. Existing reviews often have limited regional scope or small sample sizes, and several exclude non-English studies or gray literature, constraining global relevance and inclusivity. This creates a bias toward Western, higher-education contexts while neglecting diverse cultural and systemic realities. 1.1. Research questions This study investigates the applications and impact of DV and LA in supporting educational decision-making. To guide the review, the following research questions were addressed: How has research on DV and LA evolved over time, and what trends characterize publication activity across years and publication outlets? Which countries and regions contribute most to DV and LA research, and what does this reveal about global participation and collaboration? Which databases, tools, and visualization techniques are most frequently used in DV and LA research, and why do dashboards and descriptive methods dominate over advanced techniques? In which application domains are DV and LA most commonly applied, and how do these domains shape outcomes of decision-making? How does visualization affect cognitive load in educational decision-making, and what strategies are employed to balance simplicity, complexity, and interpretability? Who are the primary user groups of DV and LA systems, and how do their roles and needs influence the design and adoption of these tools? What challenges and limitations are most frequently reported in DV and LA research, and how do these constrain adoption, methodological transparency, and scalability? 1.2. Hypotheses Development Building upon the research questions, the following hypotheses are proposed to explore the applications and advantages of DV and LA systems in supporting educational decision-making. These hypotheses examine how publication patterns, geographical concentration, visualization methods, cognitive load, and user diversity influence adoption and effectiveness: H1 : Research on DV and LA has grown steadily between 2017–2024 with peaks in later years, suggesting increasing attention to visualization-supported decision-making, though unevenly distributed across time. H2 : DV and LA research is disproportionately concentrated in a few countries (USA, China, India), leaving limited representation from emerging or under-resourced regions. H3 : Dependence on Google Scholar, Scopus, and Web of Science, and the frequent use of Tableau, Power BI, and Excel, reflects accessibility and institutional familiarity, while advanced techniques remain underutilized. H4 : Dashboards, bar graphs, and line graphs dominate due to their clarity and scalability, while advanced visualizations are underreported. H5 : Education and business are the most represented domains, producing decision-making outcomes concentrated in business/industry, policy, and healthcare. H6 : Visualization design strongly influences cognitive load, with evidence split between reduction strategies (25%) and overload risks (20%), highlighting trade-offs in clarity vs. complexity. H7 : Analysts, managers, and researchers/students dominate as primary users (Fig. 16 ), while citizens and healthcare practitioners are underrepresented, suggesting unequal benefits across user categories. H8 : Persistent barriers such as complexity, scalability, interpretability, and integration challenges (Fig. 17 ) constrain adoption and methodological transparency. 1.3. Rationale The rationale for this review is to systematically examine the state of DV and LA in educational decision-making, emphasizing how geographic, institutional, and socio-economic contexts shape adoption and outcomes. Given the reliance on data-informed practices in education, it is essential to evaluate how visualization techniques and LA systems support teaching effectiveness, learning outcomes, and institutional performance. This study addresses a gap by focusing on publications between 2015–2025, synthesizing evidence to identify trends, highlight methodological gaps, and propose strategies for advancing the role of DV and LA in diverse educational contexts. 1.4. Objectives The primary objective of this review is to synthesize research on DV and LA applications in education, identifying the most common tools, techniques, and domains, and analyzing their impact on decision-making outcomes. Specific objectives are to: Examine publication and geographical trends. Identify dominant tools, techniques, and databases. Assess application domains and their decision-making contributions. Evaluate the impact of visualization design on cognitive load. Map the diversity of user groups benefiting from DV and LA. Synthesize recurring challenges and limitations constraining adoption. 1.5. Research Contributions This review contributes to the literature by: Providing a comprehensive synthesis of DV and LA studies (2015–2025) across education and related domains. Highlighting imbalances in publication trends, geographical representation, and visualization methods. Mapping outcomes on decision-making, cognitive load, and user adoption. Identifying methodological, technical, and contextual gaps that constrain scalability and inclusivity. Proposing a framework integrating inputs, context, methods, mechanisms, users, and boundaries for advancing DV and LA adoption. 1.6. Research Novelty To the best of the authors’ knowledge, this is the first review to exclusively integrate DV and LA studies in education with a focus on decision-making outcomes. The novelty lies in: A holistic evaluation of visualization tools, techniques, domains, and user groups, emphasizing their role in improving evidence-based teaching, learning, and institutional decision-making. Introducing an integrative framework that connects visualization methods, learning analytics processes, and decision outcomes, offering predictive insights for improving adoption and effectiveness in education. 2. Materials and Methods 2. Materials and Methods In this subsection, the study presents the methodology used to conduct a systematic review on the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning. The review covers literature published between 2015 and 2025. To the best of the authors’ knowledge, no comprehensive review has yet addressed this specific intersection within the stated timeframe, which underscores the novelty and contribution of this study. The research methodology involved the systematic selection of peer-reviewed articles from leading academic databases, including Scopus, Web of Science and Google Scholar, thereby ensuring a rigorous and comprehensive examination of the subject matter. 2.1. Eligibility criteria A systematic study of all peer-reviewed and published research works relevant to the study of the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning was conducted for examination. Only research works published in English between 2015 and 2025 were included in the analysis. A proper criterion for inclusion was adapted to ensure the inclusion of research papers that specifically focus on this topic and exclude those that do not. Consequently, only peer-reviewed research works that fundamentally converge on the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning, and that include a research framework or methodology specific to these aspects, were exclusively considered. The inclusion and exclusion criteria for this study are tabulated as in Table 2 (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). Table 2 Proposed Inclusion and Exclusion Criteria. Criteria Inclusion Exclusion Topic Article papers focusing on applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning Article papers not focusing on applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning Research Framework The Articles must include research framework or methodology for applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning Articles must exclude research framework or methodology for applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning Language Articles published in English language only Articles published in languages other than English Period Articles between 2015 to 2025 Articles outside 2015 and 2025 2.2. Information sources A systematic search of online databases was carried out to identify relevant studies for this review. The databases Scopus, Web of Science, and Google Scholar were selected because of their broad coverage of peer-reviewed literature in the areas of data visualization, education, and machine learning. Each database was searched thoroughly using a combination of keywords related to the study topic to ensure that the most relevant articles were captured (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). Scopus offered access to a wide range of journals and conference proceedings, while Web of Science was used to cross-check results and provide citation data to strengthen the reliability of the selected studies. Google Scholar complemented these sources by retrieving additional relevant works, including articles and dissertations that may not be indexed elsewhere. Together, the results from these three databases formed the basis of the literature review, ensuring a comprehensive and balanced collection of research works. 2.3. Search strategy The literature for this research was collected from reputable online research databases, focusing on keywords that address both the technological and contextual aspects of data visualization in education and machine learning. The inclusion of terms such as “learning analytics,” “decision-making,” and “explainable AI” ensured the capture of studies relevant to diverse educational and machine learning environments. A thorough search was carried out in three main repositories: Google Scholar, Scopus, and Web of Science. To find the most relevant studies, a specific set of keywords was used. These keywords were: ("Data Visualization" AND ("Education" OR "Learning") AND ("Decision-Making" OR "Learning Analytics" OR "Dashboard") AND ("Machine Learning" OR "Explainable AI" OR "XAI")). This combination of terms was chosen to ensure that the search captured studies directly related to the research topic. The search focused on papers published between 2015 and 2025. This time frame was selected to provide a recent and relevant overview of the subject. The search results included 101,000 papers from Google Scholar, 585 papers from Scopus, and 101 paper from Web of Science. After collecting these papers, they were carefully reviewed and filtered to select only those that were most relevant to the research questions. This process helped to narrow down the literature to the most useful and high-quality sources for this study. Table 3 shows the list of online repositories that were utilized as well as the total number of results achieved before the initial screening. The Bibliometric Analysis of Study Search Keywords is illustrated in Fig. 1 (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). Table 3 Results Achieved from Literature Search. No. Online Repository Number of results 1 Google Scholar 101,000 2 Web of Science 101 3 Scopus 585 Total 101,686 2.4. Selection process Four researchers (JM, TPM, HM) independently reviewed the titles and abstracts of the first 123 records retrieved from the search. Any differences in the selections were discussed collectively until an agreement was reached. After this initial screening, the researchers worked in pairs to independently review the titles and abstracts of all retrieved articles. In cases where differences of opinion arose, discussions were held to determine which articles should proceed to full-text evaluation. If the researchers could not reach an agreement, the third researcher was consulted to make the final decision. Afterwards, three researchers (JM, TPM, HM) independently assessed the full-text articles to determine whether they met the inclusion criteria. As before, any disagreements were resolved through discussion. If needed, the fourth researcher (BAT) was involved in making the final call on whether to include or exclude the articles, as shown in Fig. 2 (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). 2.5. Data collection process To ensure that the data collected from the studies was accurate, a structured approach was followed to minimize errors and reduce bias. Three reviewers independently extracted data from each study under the supervision of a fourth reviewer. Any discrepancies in the extracted data were discussed until a consensus was reached. A standardized data extraction form, adapted from previous systematic reviews, was used to maintain consistency across all reviewers. No automation tools were applied in the extraction process. All data were carefully entered and double-checked for accuracy to avoid errors. When information in the studies was unclear, a thorough review of all available materials was conducted, including supplementary information, appendices, and related publications, to clarify the data. In cases where concerns remained, the fourth reviewer, who is a subject matter expert, was consulted to ensure the reliability of the interpretation. For studies with multiple reports, clear criteria were established to select the most relevant version, prioritizing the most recent and comprehensive publications within the period 2015 to 2025. Where discrepancies were identified across reports, the methods and outcomes were compared in detail to resolve differences. Only studies written in English were included, while articles published in other languages were excluded to maintain consistency in the analysis and to avoid misinterpretation due to language differences, as illustrated in Fig. 3 (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). 2.6. Data items This section provides a comprehensive overview of the data items sought in this systematic review, focusing on both primary outcomes and additional variables relevant to the impact of data visualization tools and techniques on learning and decision-making in education and machine learning. The primary outcomes encompass dimensions such as improvements in learning outcomes, decision-making effectiveness, usability, user engagement, and model interpretability. In addition to these outcomes, the review also considers study and participant characteristics, intervention details, technological factors, and contextual influences, ensuring a thorough understanding of the application and effects of visualization approaches in educational and machine learning environments. This approach allows for a nuanced analysis of how data visualization contributes to enhanced learning experiences and more informed decision-making across diverse settings and conditions. 2.6.1 Data Collection Method Efforts were made to ensure a comprehensive understanding of the impact of data visualization tools and techniques on learning and decision-making in education and machine learning. Relevant outcomes were thoroughly identified and defined to capture the educational, cognitive, and technological dimensions influenced by these visualization approaches. Our approach was designed to synthesize robust evidence that reflects the transformative effects of visualization in supporting learning processes and informed decision-making. The primary outcomes of this systematic review centered on several key domains directly related to the application of data visualization in education and machine learning contexts. Learning Outcomes were a major focus, defined by measurable improvements in academic performance, knowledge retention, and student engagement. We sought all results that reflected how visualization tools supported comprehension, reduced learning difficulties, and facilitated self-regulated learning. These learning-related measures provided clear insights into the practical benefits of visualization in enhancing educational processes.Decision-Making Effectiveness was another critical outcome, assessed by examining the accuracy, speed, and quality of decisions informed by visualization tools. This included both educational decisions (such as early identification of at-risk learners or curriculum adjustments) and machine learning decisions (such as model evaluation, debugging, or interpretability). All relevant metrics that demonstrated improvements in decision-making were considered to capture a comprehensive view of visualization’s impact. Usability and User Experience were also evaluated by reviewing studies that reported on system usability, ease of interpretation, user satisfaction, and workload reduction. We specifically sought results that demonstrated how visualization tools enabled intuitive interactions, reduced cognitive load, and encouraged continued use. These measures provided valuable evidence of the human-centered effectiveness of visualization. Finally, Model Interpretability and Transparency was emphasized, particularly in machine learning contexts where explainable AI (XAI) techniques were visualized. Outcomes in this domain included user trust, understanding of model behaviour, and the ability to identify model limitations or biases. Studies reporting improvements in model interpretability through visualization were included to evaluate their role in supporting transparent and ethical decision-making. 2.6.2 Definition of Collected Data Variables In addition to the primary outcomes, several additional variables were collected to provide a deeper understanding of the context in which data visualization tools and techniques were applied. These variables were essential for interpreting the results and understanding the broader implications of visualization use in education and machine learning environments. Study characteristics were recorded, including the educational level (K-12, higher education, professional learning), subject domain, and institutional context, to assess how widely applicable the findings were across different learning settings. These details helped to situate the outcomes and highlight the diversity of approaches among the studies included. Participant characteristics were also captured, focusing on information about the users of the visualization tools such as students, instructors, administrators, or data scientists as well as their level of digital literacy and prior experience with visualization systems. This information was crucial for understanding the human factors influencing how effectively visualization tools supported learning and decision-making. Intervention characteristics were described in detail, including the type of visualization tools used (e.g., dashboards, heatmaps, learning analytics interfaces, model explanation plots), the data sources they relied on (LMS logs, assessments, clickstream data, or machine learning models), and whether the tools provided real-time or static feedback. These characteristics were key for evaluating the technological depth, usability, and integration of the interventions within the learning or ML pipeline. Other important considerations included technological and contextual factors, such as whether the visualizations were interactive, adaptive, or personalized, and how they aligned with pedagogical goals or model validation workflows. These factors allowed us to better understand not just whether visualization was used, but how it shaped user behavior and decision outcomes. Finally, external influences such as institutional policies, ethical considerations, and data privacy constraints were noted, as these can strongly affect the adoption and success of visualization approaches in education and ML contexts. As shown in Table 4 , our approach included a careful manual search across Google Scholar, Scopus, and Web of Science to ensure that the most relevant studies were captured. These searches were carefully refined to retrieve accurate and focused information, ensuring that our analysis was specific to the applications and impacts of data visualization in learning and decision-making. By clearly defining these outcomes and contextual variables, this systematic review delivers a robust and comprehensive analysis of the role of visualization tools and techniques in supporting educational and machine learning practices. This methodical approach strengthens the reliability and practical relevance of the findings, making them valuable for researchers, practitioners, and decision-makers seeking to leverage visualization for better outcomes. Table 4 Data Variables Collected. Field Description Study characteristics Educational level, subject area, and institutional context to understand the setting of each study. Participant characteristics Roles of users (students, teachers, administrators) and their level of engagement with the visualization tools. Intervention characteristics Details of visualization tools and techniques used (dashboards, heatmaps, model explanation plots), their data sources, integration with platforms (e.g., LMS, ML pipelines), and scope of application. Technological factors Whether the visualization provided real-time or static feedback, personalization or interactivity features, and alignment with learning or decision-support goals. External influences Institutional policies, data privacy requirements, ethical considerations, and other contextual factors affecting the adoption or success of visualization tools. 2.7. Study risk of bias assessment In the studies included in this review, particularly those investigating the impact of data visualization tools and techniques on learning outcomes and decision-making, it was essential to critically evaluate the risk of bias to ensure the validity and reliability of the findings. To achieve this, we applied appropriate quality assessment tools for non-randomized and experimental studies. For observational and quasi-experimental studies, the Newcastle-Ottawa Scale (NOS) was used, evaluating each study across three domains: Selection, Comparability, and Outcome. For randomized controlled trials and experimental designs, the Cochrane Risk of Bias Tool (RoB 2) was employed to assess randomization process, deviations from intended interventions, missing data, outcome measurement, and selective reporting. Each study was rated systematically, with a maximum of one star awarded per item within the Selection and Outcome categories and up to two stars for Comparability in the NOS assessment, reflecting the overall quality of the study. RoB 2 assessments were summarized as “low risk,” “some concerns,” or “high risk.” As illustrated in Fig. 4 , the risk of bias assessment was conducted by four independent reviewers (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). Each study was assessed individually to ensure objectivity, and disagreements between reviewers were resolved through discussion. Where consensus could not be reached, a fourth reviewer was consulted to make the final decision. For studies with unclear or missing methodological information particularly those involving proprietary visualization tools, learning analytics dashboards, or machine learning explainability techniques additional verification steps were undertaken. This included cross-referencing study details across reputable sources such as Scopus, Web of Science, and Google Scholar to clarify uncertainties. A comprehensive manual search was also conducted to ensure no relevant information was overlooked. No automation tools were used during this process, ensuring a careful and thorough evaluation of bias for each included study. 2.8. Synthesis methods The flow chart below in Fig. 5 illustrates the systematic approach used in our review of data visualization tools and techniques for learning and decision-making in education and machine learning (Mtjilibe et al., 2024; Khamis, 2025 ; Borrego-Ruiz & Borrego, 2025 ; Thango & Obokoh, 2024 ; Guo et al., 2025 ; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., 2025 ; Silva León et al., 2025 ; Ngcobo et al., 2024). Starting with the Study Selection Process, we identified and screened studies based on the eligibility criteria established earlier. Next, Data Standardization involved cleaning and organizing the extracted data to ensure consistency across all included studies. In the Data Analysis phase, the results were summarized and presented in tables and graphs, and initial comparisons were performed to highlight trends in learning outcomes, decision-making improvements, usability, and model interpretability. The flow then moves to Heterogeneity Assessment, where we evaluated variability between studies through subgroup analysis, comparing factors such as visualization type, educational level, and decision-making context. Finally, Bias Assessment was carried out to identify potential biases and ensure transparency in our review process. This structured approach ensures that the findings of this review are comprehensive, reliable, and reproducible. In this systematic review on the application and impact of data visualization tools and techniques for learning and decision-making in education and machine learning, we employed rigorous synthesis methods to ensure that our results were robust, transparent, and reproducible. To determine the eligibility of studies for synthesis, we meticulously tabulated the characteristics of each study and compared them against our predefined synthesis groups. This approach allowed us to include only the most relevant studies, ensuring that our findings were both valid and closely aligned with the objectives of the review. In preparing the data for synthesis, we addressed any missing information by reviewing supplementary materials and, where necessary, standardizing outcome measures to maintain consistency across studies. The results were presented using structured tables and visual summaries, such as bar charts and comparative graphs, which provided a clear representation of key outcomes and helped to identify trends, patterns, and outliers effectively. The synthesis of results was conducted using a narrative and, where appropriate, quantitative approach, with subgroup analyses focusing on factors such as type of visualization (e.g., dashboards, heatmaps, model explanation plots), educational level, and decision-making context. This approach provided nuanced insights into how these variables influenced learning outcomes, usability, and decision-making effectiveness. Heterogeneity was further explored through subgroup comparisons to identify potential sources of variation, such as interactivity level or real-time feedback features. Sensitivity analyses were also carried out to assess the robustness of the findings, ensuring that the conclusions drawn were supported by consistent and reliable evidence. Through this comprehensive and systematic approach, we were able to provide a meaningful aggregation of the evidence, offering valuable insights for educators, researchers, and decision-makers seeking to leverage visualization tools and techniques to enhance learning outcomes and support informed decision-making in education and machine learning environments. 2.8.1. Eligibility for Synthesis To determine study eligibility for inclusion in our systematic review on data visualization tools and techniques for learning and decision-making in education and machine learning, each study was carefully evaluated for its relevance and alignment with the review’s objectives. We manually assessed and compared each study’s characteristics such as the type of visualization tool, data source, educational or machine learning context, and reported outcomes—against our predefined synthesis groups. A matrix was created to visually compare the scope and methodologies of the studies with our inclusion criteria, ensuring a thorough and objective evaluation. This process ensured that only studies directly relevant to the role of data visualization in supporting learning and decision-making were included, thereby improving the overall rigor, reliability, and focus of the review. 2.8.2. Data Preparation for Synthesis In this review, data preparation involved converting and standardizing information extracted from the included studies on data visualization tools and techniques to ensure consistency before synthesis. For example, when visualization outcomes or effectiveness measures were reported differently across studies, mathematical adjustments were applied to convert these into a uniform scale, enabling comparability. In addition, handling missing data was a crucial aspect of the analysis. When key indicators, such as effectiveness percentages, visualization performance metrics, or decision-making outcomes, were not fully reported, we employed established methods such as data triangulation and, where appropriate, statistical imputation to estimate missing values. This process ensured that the dataset remained comprehensive and reliable, thereby enhancing the robustness of the analysis and allowing for more accurate synthesis of findings across educational and machine learning contexts. 2.8.3. Tabulation and Visual Display of Results Results from individual studies and synthesis efforts were organized using both tabular and graphical methods to enhance clarity and facilitate cross-comparison. Tabular structures were employed to present the data in a structured format, where outcomes were categorized by domains such as visualization tools, visualization techniques, learning contexts, and decision-making impacts. Within each domain, studies were ordered according to their methodological rigor and assessed risk of bias, ensuring that the most reliable evidence was highlighted. In addition to tabular presentation, graphical methods were used to visually summarize findings across studies. Comparative charts and Sankey diagrams were employed to map the relationships between visualization tools, techniques, and educational or machine learning applications. Network diagrams were also used to depict co-occurrence of visualization methods with decision-making outcomes. These visual displays allowed trends to be revealed over time and across different contexts, facilitating the identification of gaps, dominant approaches, and underrepresented methods within the literature. 2.8.4. Synthesis of Results During our manual search across online repositories such as Google Scholar, Scopus, and Web of Science, we systematically reviewed and synthesized the results of relevant studies on data visualization tools and techniques. The synthesis process was guided by the type of data reported and the variability observed across studies. To account for methodological and contextual differences, we evaluated the applicability of both descriptive and comparative synthesis approaches, depending on the level of heterogeneity among study outcomes. The choice of synthesis method was informed by the characteristics of the data and our assumptions about consistency in reported impacts across different educational and machine learning contexts. After exporting the extracted data into Excel, we created comparative charts and visual mappings (e.g., Sankey diagrams, heatmaps, and trend analyses) to inspect the distribution of visualization tools, techniques, and outcomes. This initial visual inspection enabled us to identify recurring patterns, gaps, and areas of divergence across studies, offering a more nuanced understanding of how visualization contributes to learning enhancement and decision-making effectiveness. 2.8.5. Exploring Causes of Heterogeneity Subgroup analyses were conducted to explore potential sources of heterogeneity, such as differences in study settings, visualization tools employed and reported outcome measures. Specific analyses focused on factors like the educational context (e.g., higher education, K–12, online learning), the type of visualization tool or technique used (e.g., dashboards, heatmaps, storytelling, interactive graphs), and the application domain (education versus machine learning). We also examined cognitive load considerations, user types (e.g., students, analysts, educators), and geographic location to assess how these factors influenced the effectiveness of visualization in supporting learning and decision-making. These analyses helped identify underlying patterns and relationships that contributed to variability across studies, highlighting the conditions under which visualization techniques are most effective. 2.8.6. Sensitivity Analyses Sensitivity analyses were conducted to evaluate the robustness of the synthesis results in relation to the assumptions and methodological choices made during the review. These analyses included testing the impact of excluding studies that were assessed as having a high risk of bias, as well as examining how the results changed when alternative synthesis approaches (e.g., narrative vs. quantitative comparison) were applied. We also explored the influence of studies that reported incomplete or inconsistent outcome measures, such as engagement levels, decision-making accuracy, or cognitive load, to ensure that findings were not disproportionately shaped by a small subset of studies. This process strengthened the reliability and validity of the conclusions by addressing potential sources of bias and confirming that the overall patterns observed remained consistent across different analytical scenarios. 2.9. Reporting bias assessment In conducting our systematic review on the application of data visualization tools and techniques for learning and decision-making in education and machine learning, it was crucial to assess the risk of bias due to potentially missing results, particularly those arising from selective publication or selective reporting of outcomes. We recognized that such biases could significantly affect the validity and reliability of our synthesis, and thus, we employed a structured and rigorous approach to address this concern. Our assessment of reporting bias was carried out using a combination of established statistical and graphical methods. Specifically, contour-enhanced funnel plots were utilized as a visual tool to detect asymmetries in the data. These plots were carefully examined to determine whether missing studies were more likely due to reporting bias or chance. The inclusion of statistical significance contours enabled a clear differentiation between the two, offering a reliable visual representation of potential biases. For this assessment, we did not develop new tools but relied on widely accepted techniques extensively documented in prior systematic reviews. The methodological rigor of these tools was central to our process. Contour-enhanced funnel plots provided a straightforward yet effective way to evaluate the distribution of studies, allowing us to detect and account for reporting biases in our synthesis. The assessment was designed to minimize subjectivity, ensuring the robustness of our findings. Multiple independent reviewers were involved in this process, and any disagreements were resolved through consensus discussions or, when necessary, by consulting a methodological expert. This collaborative approach strengthened the objectivity of our interpretations. We deliberately avoided automation tools for this stage, instead using manual approaches such as creating charts and plots in Excel. This hands-on method allowed for close inspection of the data, ensuring that subtle patterns or potential biases were not overlooked. To further validate our results, comprehensive manual searches were conducted across multiple repositories, including Google Scholar, Scopus, and Web of Science. These cross-references were essential in identifying discrepancies and ensuring completeness, thereby reinforcing the reliability of our conclusions. Given the specific context of visualization studies in education and machine learning, we adapted standard bias assessment methods to better reflect the reporting practices of this field. Visualization-focused studies often differ in reporting style from other domains such as medicine or business, necessitating these contextual adaptations. By tailoring our methods to align with the nature of the studies reviewed, we ensured methodological soundness and contextual accuracy. To promote transparency and reproducibility, all approaches employed in this review are thoroughly documented and made available in the supplementary materials. This commitment to openness allows other researchers to replicate our analysis or build upon it in future work, thereby enhancing the rigor and reliability of systematic research on data visualization for learning and decision-making. 2.10. Certainty assessment The reviewed literature was evaluated based on five quality assessment (QA) criteria to ensure rigor and relevance: QA1: The clarity and explicitness of the research aim. QA2: The specification and transparency of data collection methods. QA3: The clear definition and explanation of the data mining and business intelligence processes. QA4: The application of a well-defined and appropriate research methodology. QA5: The contribution of the research findings to the enhancement of existing literature on Data Visualization Tools and Techniques for Learning and Decision-Making in Education and Machine Learning. The certainty assessment responses are rated on a scale from zero (0) to one (1). A 'No' response is assigned '0' points, a score of '0.5' is given if the criterion is 'Partially' met, and '1' point is assigned for a 'Yes' response. All five criteria are scored using this scale. Each piece of literature under review can receive a total score between 0 and 5 points. The results of the certainty assessment for the collected literature on the applications of data visualization tools and techniques in education and machine learning are presented in Table 5 . Table 5 Certainty Assessment Results for Collected Literature on Data Visualization Tools and Techniques for Learning and Decision-Making in Education and Machine Learning. Ref. QA1 QA2 QA3 QA4 QA5 Total % grading (Gonçalves, T., Maciel, C., & Rodrigues, R. 2017) ;(D’Alessio, F., Aitella, R., Giannini, M., & Burrai, R. 2024); (Liu, Y. (2025); (Oral, A., Chawla, N., Wijkstra, H., Mahyar, N., & Dimara, E. 2025). 1 0 0.5 0 1 2.5 50 (Azevedo, R., et al. ( 2017 ); Zhu, Y. 2017) ;(Wang, Y., et al. 2024); (Chakraborty, A., et al. 2024); (Kumar, R. 2024);. 0.5 0.5 0.5 0.5 1 3 60 (Zhu, Y., et al. 2018);( Dimara, E., & Stasko, J. 2018). 1 0.5 0.5 1 0.5 3.5 70 (Zhu, Y., Gonçalves, T., & Rodrigues, R. 2018);( Dimara, E., & Stasko, J. 2018); (Alhadad, S. 2018); (Paiva, R., et al. 2018 ); (Bergram, S., & Ochan, J. 2018); (Huang, Y., et al. 2018); (Sosulski, K. 2018 );( Lacefield, R., & Applegate, L. 2018); (Tantalaki, N., et al. 2018); (Bergram, S., & Ochan, J. 2018); (Sosulski, K. 2018 ). 1 0.5 1 1 0.5 4 80 (Wolfert, S., Ge, L., Verdouw, C., & Bogaardt, M. 2017); (Strandberg, R., et al. (2017); Janssen, M., & Helbig, N. 2017); (Zhu, Y. 2017) 1 1 1 1 0.5 4.5 90 (Perdana, A., Robb, A., & Rohde, F. 2019 );( Bhat, P. 2017); (Buenaño-Fernández, D. 2017);(Dimara, E., & Stasko, J. 2018); (Alhadad, S. 2018);( Hoelscher, C., & Mortimer, M. 2018); (Bergram, S., & Ochan, J. (2018); (Huang, Y., Wu, M., Wang, Y., & Ouyang, L. (2018); (Sosulski, K. 2018 ); (Tantalaki, N., Souravlas, S., & Roumeliotis, M. 2018);( Sedrakyan, G. 2019); (Börner, K., Bueckle, A., & Ginda, M. 2019 ); (Sight and Life Magazine. 2019); (Levy-Fix, G., Kuperman, G., & Elhadad, N. 2019); (Aung, T., et al. 2019 ); (Luo, W. 2019 ); (Li, X., et al. 2019); (Milligan, R. 2019); (Stanca, C., et al. 2019 ); (Guarese, R., et al. 2020 ); (Redondo, E., et al. 2020 ); (Peddoju, S., & Upadhyay, A. 2020); (Briggs, M. 2020); (Cheng, J., et al. 2020); (Rawat, P., et al. 2021);( Kumar, S., et al. 2021); (Dy, A., et al. 2021 ); (Alshareef, A., et al. 2021 ); (Talukder, M., & Deb, K. 2021); (Cepero, M., et al. 2021); (Rodríguez-Echeverría, S. 2021); (Fernández-García, J. C. 2021); (Gore, C., & Odisho, K. 2021); (Conejero Manzano, J., et al. 2021);( Moh’d Ali, H., et al. 2021); (Zytek, A., et al. 2021 ); (Yuan, Y., Liu, H., & Kuang, W. 2021); (Dimara, E., et al. 2021 ); (Mahmud, M., et al. 2022); (Vallet, F., et al. 2022); (Sakib, S. 2022); (El Morr, C., et al. 2022); (Martins, A., et al. 2022); (Murumba, S. 2022);( Patel, R. 2022); (Zheng, Y., et al. 2022); (Ak, F. 2022);( Pera, A. 2022 ); (Jenkins, J. 2022); (Kamolsin, T., & Phu, S. 2022); (Donohoe, P., & Costello, F. 2022); (Bali, S., et al. 2022 ); (Martynenko, A., et al. 2022); (Kamissoko, D., et al. 2022 ); (Ren, Y. 2022); (Zhang, L., et al. 2023); (Pazouki, M., et al. 2023); (Diao, H., & Wei, S. 2023); (Bertone, E., & Stewart, R. A. 2023); (Llaha, A., Aliu, D., & Kadëna, A. 2023); (Rahimi Ardabili, F., et al. 2023) ; (Ouyang, L. 2024);( Shahidan, S., et al. 2024); (Mahyar, N., & Dimara, E. 2024); (Shinde, A. 2024); (Hossain, M., Yasmin, F., Biswas, T., & Asha, S. 2024); (Uddin, M. 2024); (Shahidan, S., Ibrahim, H., & Jamaluddin, A. 2024); (Bach, J., et al. 2024); (Chen, L., et al. 2024); (Sotiropoulos, D., Giormezis, N., Pertsas, D., & Tsirkas, N. 2024);( Zheng, Y., Lillis, D., & Campbell, R. 2024); (Romero-Organvidez, F., Horcas, J., Galindo, J., & Benavides, D. (2024); (Yin, H., et al. 2024);( Mauludina, E., Mulyani, H., Winarningsih, S., & Susanto, A. 2024); (Geisler, M., & Allwood, C. (2024); Then, E., & Bigby, C. 2024); (Aluja, T., Balada, F., García, J., & García, P. 2024); (Kollar, J., Kika, K., & Mazurova, L. 2025);( Zaheer, H., Hanif, A., Sarwar, M., & Talib, M. 2025); (Pham, T., et al. 2025); (Grolli, R., et al. 2025). 1 1 1 1 1 5 100 To support the conclusions of this systematic review on the applications of data visualization tools and techniques for learning and decision-making in education and machine learning, we undertook a rigorous assessment of the certainty of the evidence. The strength and reliability of our findings depend on a systematic evaluation process, which we carried out using the GRADE (Grading of Recommendations, Assessment, Development, and Evaluations) framework. GRADE is a globally recognized system that offers a comprehensive and transparent approach to assessing the quality of evidence, ensuring that the conclusions drawn are both credible and well-founded. The certainty of the evidence across key outcomes was meticulously evaluated using several critical factors. First, we closely examined the precision of reported measures by considering sample sizes and the clarity of outcome reporting across the studies. Narrow confidence intervals coupled with large or well-defined samples were indicative of a high level of certainty in the evidence, as they suggest more reliable and precise estimates of visualization impacts. We also assessed the consistency of findings by comparing results across included studies. High consistency, where studies demonstrated similar effects (e.g., on engagement, decision accuracy, or cognitive load), contributed to greater certainty. Any observed heterogeneity was thoroughly analysed to understand its sources and potential influence on the overall findings. Furthermore, the potential for bias was evaluated using an adapted version of the Cochrane Risk of Bias tool. Studies with a low risk of bias were considered to contribute more significantly to the overall certainty of the evidence. We also judged directness based on the alignment of study populations, interventions, and outcomes with the research questions of this review. High directness such as studies explicitly focusing on visualization for educational or machine learning decision-making strengthened the support for our conclusions, leading to greater confidence in the evidence. Based on these factors, the certainty of evidence was categorized as follows: High certainty was assigned when studies were consistent, precise, directly applicable, and exhibited a low risk of bias. Moderate certainty was applied when there were minor concerns about one factor, such as some inconsistency or a moderate risk of bias. Low certainty was given when significant concerns existed in multiple areas, including imprecision, inconsistency, or a high risk of bias. Very low certainty was assigned when critical issues were present across all factors, significantly undermining confidence in the results. To ensure the relevance of the GRADE approach to this review, we adapted it specifically for outcomes related to visualization effectiveness, including learning enhancement, cognitive load management, and decision-making improvements in education and machine learning contexts. Multiple independent reviewers assessed the certainty of evidence for each outcome. Disagreements were resolved through consensus discussions, ensuring a balanced and thorough evaluation. Additionally, where possible, we sought supplementary data or clarification from study authors to support the certainty assessments. 3. Results 3.1. Study selection In this systematic review, the study selection process followed a rigorous and structured approach to ensure the inclusion of relevant and high-quality research articles. Three prominent online databases Google Scholar, Web of Science, and Scopus were systematically searched to identify studies that met the inclusion criteria. Specifically, the search retrieved 101 000 records from Google Scholar, 101 record from Web of Science, and 585 records from Scopus, resulting in a total of 101 685 initial records. Following this, duplicate entries were removed, leaving 37074 unique records. These records underwent a preliminary screening process, during which their titles and abstracts were assessed for relevance to the review’s criteria. This step resulted in the selection of 34 full-text documents for a more detailed evaluation. After a comprehensive review of these full-text documents, 123 studies were deemed eligible for inclusion in the final systematic review. The included studies consisted of 67 journal articles, 4 book chapters, 32 conference papers, and 1 dissertation. The overall study selection process is depicted in Fig. 6 , which provides a detailed PRISMA flowchart outlining the progression of records through each stage of the review. Additionally, the distribution of articles obtained from each database is illustrated in Fig. 7 , highlighting the contributions of the three databases to the final pool of studies. These visualizations enhance the transparency of the selection process and facilitate the replication of this methodology by other researchers. 3.2. Research Distribution by Published Works The temporal distribution of research outputs reveals varying intensities of scholarly focus across the observed years. As illustrated in Fig. 7 , publication activity demonstrates periods of steady growth interspersed with notable fluctuations. Between 2017 and 2019, there was a consistent rise in published works, followed by a visible decline in 2020. This dip may be attributed to contextual factors such as global disruptions to academic activity. A renewed surge in publications is observed from 2021 onward, culminating in a significant peak in 2024, which marks the highest volume of research outputs within the period. The decline recorded in 2025, although provisional, suggests an incomplete data capture for the year rather than a definitive reduction in scholarly output. 3.3. Country Distribution of Reviewed Papers The geographical distribution of research contributions reveals a marked imbalance across countries. As shown in Fig. 8 , a majority of publications originate from a small group of nations. The United States leads with 24.39% of the reviewed works, followed closely by China (18.70%) and India (10.57%). Other significant contributors include Brazil, France, Germany, and the UK, each contributing between 5–9%. These countries collectively constitute the “high contribution” group, which accounts for approximately 85% of the total reviewed works. A “moderate contribution” cluster, ranging between 2–5%, includes nations such as Malaysia, Romania, Spain, Bangladesh, and Greece. Meanwhile, the “low contribution” group (below 2%) is comprised of a wider set of countries—including Ukraine, Hungary, Indonesia, Saudi Arabia, and others—that collectively represent 12% of contributions. 3.4. Distribution of Publications The analysis of publication types reveals a strong preference for traditional scholarly outlets. As presented in Fig. 9 , journal articles dominate with 69.92% of the reviewed works, reflecting their established role as the primary medium for disseminating peer-reviewed knowledge. Conference papers account for 26.02%, underscoring their significance as venues for presenting emerging findings, networking, and receiving timely feedback within academic and professional communities. In contrast, book Chaps. (3.25%) and dissertations (0.81%) represent a relatively minor proportion, collectively falling within the low-contribution category (< 5%). Their limited presence suggests that while these forms provide specialized or exploratory insights, they remain less central to mainstream scholarly communication in this domain. 3.5. Distribution of Databases Used An examination of the databases employed in the reviewed studies highlights the dominance of a few indexing platforms. As shown in Fig. 10 , Google Scholar was the most frequently utilized source, accounting for 52.03% of the studies. Its accessibility and wide coverage likely contribute to its prominence, especially for interdisciplinary and exploratory research. Scopus follows with 30.08%, reflecting its strong reputation for indexing peer-reviewed and high-quality academic outputs. Meanwhile, the Web of Science represents 17.89% of usage, emphasizing its role in providing rigorously curated bibliographic records. The reliance on these three databases illustrates both a preference for comprehensive accessibility and the perceived authority of established indexing services. 3.6. Distribution of Visualization Tools The reviewed studies employed a diverse range of visualization tools, reflecting both accessibility and domain-specific preferences. As illustrated in Fig. 11 , Tableau emerged as the most widely used tool (44.72%), highlighting its popularity for interactive dashboards and intuitive visual analytics. Power BI (14.63%) and MS Excel (8.94%) followed, indicating strong reliance on business intelligence and traditional spreadsheet-based tools. Programming-based tools such as Python (8.13%), Matplotlib (8.13%), and Seaborn (5.69%) were also frequently applied, demonstrating the growing integration of data science approaches in visualization research. Specialized platforms like VOSviewer (3.25%) catered to bibliometric and network analysis. Less frequently cited tools, including D3.js, JavaScript, scikit-learn, and Taiwan-specific platforms (each < 1%), suggest niche but important contributions to visualization diversity. 3.7. Distribution of Visualization Techniques The reviewed studies applied a variety of visualization techniques, reflecting the multidimensional purposes of data-driven decision-making. As shown in Fig. 12 , dashboards were the most dominant (26.83%), underscoring their value in integrating diverse data sources into interactive and actionable interfaces. Traditional forms such as bar graphs (16.26%) and line graphs (12.20%) remained widely used, emphasizing their clarity and accessibility for general audiences. Advanced techniques like heatmaps (11.38%), scatter plots (8.94%), and time series graphs (5.69%) were frequently adopted for trend detection, correlation analysis, and temporal monitoring. Meanwhile, approaches such as storytelling (10.57%), bubble charts (4.88%), and trend graphs (3.25%) highlight efforts to enhance interpretability and engagement, particularly in conveying complex insights to decision-makers. 3.8. Distribution of Application Domains The reviewed studies covered diverse domains, with the strongest emphasis on education (43.09%), reflecting the increasing role of visualization in pedagogy, learning analytics, and evidence-based curriculum design. The business domain followed closely (39.84%), where visualization is frequently applied to decision support, performance monitoring, and strategic planning. Meanwhile, policy applications (17.07%) were less prevalent but remain essential in guiding governance, sustainability, and regulatory interventions. As shown in Fig. 13 , these domains map onto different intensity levels: education aligns mostly with moderate usage (5–25%), while business shows a stronger presence in the high category (> 25%), highlighting its strategic reliance on advanced visualization. Policy remains comparatively lower but steadily growing in visibility. 3.9. Decision-Making Outcomes The outcomes of visualization-supported decision-making span multiple dimensions. As shown in Fig. 14 , the most common focus was on business and industry outcomes (30%), where visualization enhanced performance tracking, resource optimization, and strategic planning. This was followed by policy and governance (15%) and healthcare & clinical applications (15%), demonstrating growing adoption of visualization for managing public health, clinical diagnostics, and regulatory oversight. Other identified outcomes include tool evaluation and framework testing (10%), decision accuracy and quality (10%), and educational impact (10%), where visualization strengthened learning gains, interpretability, and evidence-based instruction. Collectively, these findings illustrate that visualization does not serve only technical efficiency but also broader societal and institutional goals. 3.10. Outcomes on Cognitive Load Studies addressing visualization and decision-making frequently focused on how design choices shape cognitive load. As illustrated in Fig. 15 , the most prominent strategies were cognitive load reduction approaches (25%) and simplicity and clarity in design (20%), both of which highlight the importance of minimizing unnecessary complexity in visual outputs. Conversely, a notable share of studies (20%) still identified complexity and overload risks, underscoring challenges related to high-dimensional data and poorly designed interfaces. Meanwhile, user-centered adaptation (10%) and interactive or immersive solutions (10%) reflect efforts to align visualization with user needs and emerging technologies. Finally, applied or domain-specific practices (15%) suggest that effective strategies must often be tailored to the context of use, such as education, healthcare, or business decision environments. 3.11. User Groups The reviewed studies targeted a variety of user groups, reflecting the diverse contexts in which visualization supports decision-making. As shown in Fig. 16 , the largest share was directed toward analysts (32.52%), who rely on visualization for technical and operational insights. Managers (19.51%) and researchers (17.07%) followed, highlighting the use of visualization both for decision-making in professional settings and for knowledge production in academia. Students (17.07%) also represented a significant group, demonstrating visualization’s role in learning, skill development, and educational engagement. Other identified groups include healthcare practitioners (7.32%), citizens (5.69%), and data scientists (0.81%), the latter reflecting a more niche but growing specialization in technical applications. These clusters map onto broader categories such as professional/technical users, decision-makers, academic learners and producers, domain-specific practitioners, and civic users, emphasizing the widespread but differentiated adoption of visualization across domains. 3.12. Challenges and Limitations The reviewed literature identified several recurring challenges and limitations that influence the effectiveness and applicability of visualization in decision-making contexts. As shown in Fig. 17 , the most prominent concerns include complexity and scalability (20%) and cognitive and interpretability issues (18%), both of which highlight the difficulty of balancing technical sophistication with clarity and usability. Other recurring themes were data quality and integration (15%), technical and tool limitations (14%), and user training and literacy gaps (12%), which underline barriers to adoption across diverse contexts. Additionally, concerns around evaluation and evidence gaps (10%), ethical and social issues (7%), and global relevance and generalizability (4%) suggest that while visualization is a powerful tool, its reliability and inclusivity remain constrained. Together, these findings reveal the importance of methodological rigor, equitable design, and training support to ensure visualization reaches its full potential. 4. Proposed Framework for Visualization in Decision-Making 4.1. Inputs: Knowledge Sources and Research Channels The framework begins with scholarly inputs, which were shaped by the dominant role of journal articles and conference papers (Fig. 9 ) and retrieved primarily from Google Scholar, Scopus, and Web of Science (Fig. 10 ). These sources form the knowledge base that drives methodological diversity and ensures academic rigor. 4.2. Contextual Dimensions: Geographic and Domain Distributions Research is geographically concentrated in a few countries (USA, China, India, Brazil, France, UK, Germany), reflecting knowledge asymmetry (Fig. 8 ). Domains of application—education, business, and policy (Fig. 13 )—shape the way visualization tools are applied, with education focusing on engagement, business on strategy, and policy on governance. 4.3. Methods: Tools and Techniques Visualization practices draw from a wide spectrum of tools—ranging from Tableau, Power BI, and Excel to Python and Matplotlib (Fig. 11 )—and techniques such as dashboards, bar graphs, line charts, and storytelling (Fig. 12 ). Together, these form the operational core of visualization-supported decision-making, balancing traditional clarity with interactive innovation. 4.4. Mechanisms: Cognitive and Decision Processes The cognitive layer addresses how visualization influences decision-making through: Cognitive load management (Fig. 15 ), via strategies such as simplification, clarity, and adaptive design. Decision-making outcomes (Fig. 14 ), spanning improved business performance, educational impact, healthcare, and governance. This layer represents the mechanism of translation: how raw data, once visualized, becomes actionable insight. 4.5. Users: Target Groups and Roles Different user groups shape adoption and interpretation (Fig. 16 ). Analysts, managers, and researchers dominate, but learners (students) and practitioners (healthcare, citizens) emphasize inclusivity. The framework thus highlights tailored visualization strategies based on user literacy, technical capacity, and decision context. 4.6. Boundaries: Challenges and Limitations Finally, the framework is bounded by structural challenges (Fig. 17 ): Complexity and scalability issues (20%), Cognitive/interpretability barriers (18%), Data quality/integration constraints (15%), and User literacy gaps (12%). These challenges define the limits of transferability and point toward areas requiring future innovation. 5. Discussion 5.1. How has research on data visualization and learning analytics evolved over time? The temporal distribution of reviewed works shows clear fluctuations in scholarly activity. Between 2017 and 2019, there was a steady rise in publications, followed by a noticeable dip in 2020, likely reflecting disruptions in academic research activity. From 2021 onward, the field regained momentum, culminating in a remarkable peak in 2024 — the highest year of publication output (Fig. 7 ). The decline observed in 2025 is likely provisional, reflecting incomplete data capture rather than a genuine reduction. These patterns suggest that DV and LA research has grown in relevance over time, particularly in response to increasing demands for evidence-driven decision-making. 5.2. Which countries and regions contribute most to this research field? The geographical distribution demonstrates a pronounced imbalance (Fig. 8 ). The United States (24.39%), China (18.70%), and India (10.57%) dominate, together accounting for over half of the publications. Other notable contributors include Brazil, France, Germany, and the UK (5–9% each), forming a high-contribution cluster of around 85% of total output. By contrast, moderate contributors such as Malaysia, Romania, and Spain (2–5%), and a large set of low contributors (< 2%), underscore the global unevenness of research capacity. This suggests the need for more inclusive, cross-regional collaboration to ensure broader perspectives in visualization and learning analytics research. 5.3. What publication outlets are most common? Journal articles remain the dominant outlet, representing 69.92% of the reviewed works (Fig. 9 ). This reflects the centrality of peer-reviewed journals in shaping scholarly discourse. Conference papers, at 26.02%, play a vital complementary role, especially for emerging ideas and community engagement. Book Chaps. (3.25%) and dissertations (0.81%) are comparatively underrepresented, indicating that specialized or exploratory contributions remain less mainstream. This publication distribution emphasizes the prioritization of rigor and peer-review while still allowing space for exploratory dissemination. 5.4. Which databases are most frequently used in this research? Google Scholar is the most widely used source, accounting for 52.03% of studies, followed by Scopus (30.08%) and Web of Science (17.89%) (Fig. 10 ). The reliance on Google Scholar highlights its accessibility and inclusiveness but also raises questions about selectivity and quality control. Scopus and Web of Science provide stronger filtering and indexing standards, yet their lower shares suggest barriers in access or coverage. This distribution underscores a trade-off between comprehensiveness and methodological rigor in database selection. 5.5. What visualization tools and techniques are most applied? Tableau emerges as the leading tool (44.72%), followed by Power BI (14.63%) and MS Excel (8.94%) (Fig. 11 ). This highlights the dominance of user-friendly, business-intelligence–oriented platforms. Programming-based tools like Python (8.13%), Matplotlib (8.13%), and Seaborn (5.69%) represent growing but still secondary approaches. Less frequently applied tools (e.g., VOSviewer, D3.js) remain niche. On techniques, dashboards dominate (26.83%), reflecting their value in integrating data into actionable formats (Fig. 12 ). Traditional methods such as bar graphs (16.26%) and line graphs (12.20%) remain foundational, while advanced approaches like heatmaps (11.38%), scatter plots (8.94%), and storytelling (10.57%) indicate attempts to balance analytical depth with user engagement. Collectively, these findings reveal both continuity with conventional methods and increasing diversification into interactive and immersive techniques. 5.6. In which domains is DV and LA most applied? The largest share of studies focus on education (43.09%), underscoring the importance of visualization for pedagogy, learning analytics, and institutional decision-making (Fig. 13 ). Business (39.84%) closely follows, highlighting its strategic reliance on visualization for operational and managerial decision-making. Policy (17.07%) applications remain less developed but are gaining visibility, particularly in governance and sustainability contexts. These distributions reflect both the dominance of established application areas and the potential for growth in underexplored domains. 5.7. What outcomes are associated with visualization-supported decision-making? Decision-making outcomes are diverse (Fig. 14 ). The most common are business and industry outcomes (30%), where visualization supports performance tracking and resource optimization. Policy and governance outcomes (15%) and healthcare/clinical applications (15%) reveal growing institutional and societal uptake. Educational outcomes (10%), decision accuracy and quality (10%), and tool/framework evaluations (10%) further emphasize the broad impact of visualization. These findings suggest that DV and LA are not limited to efficiency gains but contribute meaningfully to learning, governance, and healthcare. 5.8. How does visualization affect cognitive load in decision-making? The literature identifies both benefits and risks (Fig. 15 ). Strategies to reduce cognitive load (25%) and emphasize simplicity and clarity in design (20%) are prominent, highlighting their role in facilitating user comprehension. However, complexity and overload risks remain significant (20%), often arising from poorly designed or high-dimensional visuals. User-centered adaptation (10%), interactive/immersive solutions (10%), and domain-specific practices (15%) show promising strategies to tailor visualization effectively. Together, these results suggest that while visualization can mitigate cognitive burden, careful design choices are critical to avoid unintended overload. 5.9. Who are the primary user groups? The distribution of user groups reveals that analysts (32.52%) dominate, reflecting the technical and operational nature of much of this research (Fig. 16 ). Managers (19.51%) and researchers (17.07%) represent additional large groups, highlighting both decision-making and academic knowledge production. Students (17.07%) reflect the educational emphasis of the field, while healthcare practitioners (7.32%), citizens (5.69%), and data scientists (0.81%) represent smaller but important communities. These findings suggest that visualization research is heavily skewed toward professional and technical users but has meaningful extensions into education and public engagement. 5.10. What challenges and limitations persist? As summarized in Fig. 17 , challenges include complexity and scalability (20%), cognitive and interpretability issues (18%), data quality and integration (15%), and tool/technical limitations (14%). User training and literacy gaps (12%) further restrict uptake. Additionally, evaluation and evidence gaps (10%), ethical and social concerns (7%), and issues of global relevance (4%) highlight persistent barriers. These challenges emphasize the need for methodological rigor, equitable design, and capacity building to ensure the sustainable adoption of DV and LA across diverse contexts. 6. Conclusion This review synthesized 123 studies (2015–2025) to evaluate the applications and impact of data visualization (DV) and learning analytics (LA) in supporting educational decision-making. To structure the evidence, a taxonomy was developed encompassing visualization tools, visualization techniques, application domains, decision-making outcomes, cognitive load considerations, user groups, and reported challenges. Findings reveal a steady growth in research outputs with notable peaks between 2021–2024 (Fig. 7 ), though contributions remain geographically concentrated in the USA, China, and India (Fig. 8 ). Journal articles dominated publication outlets (Fig. 9 ), and Google Scholar, Scopus, and Web of Science were the most common sources (Fig. 10 ). Tool distribution was led by Tableau, Power BI, and Excel (Fig. 11 ), while dashboards, bar graphs, and line graphs emerged as the most frequently applied techniques (Fig. 12 ). Education and business were the leading application domains (Fig. 13 ), with decision-making outcomes most prominent in business/industry, policy, and healthcare (Fig. 14 ). Cognitive load outcomes highlighted both the benefits of simplicity and risks of overload (Fig. 15 ), underscoring trade-offs between clarity and complexity. User groups were led by analysts, managers, and researchers/students, while healthcare practitioners and citizens were comparatively underrepresented (Fig. 16 ). Persistent challenges included complexity and scalability (20%), interpretability (18%), data integration (15%), and training gaps (12%) (Fig. 17 ). These results emphasize three critical insights. First, methodological transparency and standardized reporting remain limited, particularly regarding tool selection and visualization design. Second, reliance on descriptive dashboards reflects underutilization of advanced methods such as predictive modeling and network analysis, restricting the field’s capacity to fully support evidence-based education. Third, user diversity and contextual variation are often overlooked, with limited attention to K–12, resource-constrained, or non-Western environments.To address these gaps, future research should pursue (i) rigorous methodological frameworks and longitudinal validation studies, (ii) hybrid visualization models integrating advanced analytics with user-centered design, and (iii) comparative analyses across regions and institutional contexts to promote inclusivity and scalability. A conceptual framework (Fig. 18) is proposed to integrate inputs, context, methods, mechanisms, users, and boundaries, offering a structured pathway for advancing DV and LA adoption in education. References Buenaño-Fernández, D. (2019). The use of tools of data mining to decision making in engineering education—A systematic mapping study. Computer Applications in Engineering Education, 27 (6), 1633–1651. https://doi.org/10.1002/cae.22100 Zhu, Z. (2017). Interactive data visualization techniques applied to healthcare decision making. In Computer Science & IT (pp. 1–15). IGI Global. https://doi.org/10.4018/978-1-5225-1994-7.ch001 Anderson, J. S., & Williams, S. K. (2019). Turning data into better decision making: Asking questions, collecting and analyzing data in a personal analytics project. Decision Sciences Journal of Innovative Education, 17 (2), 126–145. https://doi.org/10.1111/dsji.12173 Chatti, M. A., Dyckhoff, A. L., Schroeder, U., & Thüs, H. (2012). A reference model for learning analytics. International Journal of Technology Enhanced Learning, 4 (5/6), 318–331. https://doi.org/10.1504/IJTEL.2012.051816 Ferguson, R. (2012). Learning analytics: Drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4 (5/6), 304–317. https://doi.org/10.1504/IJTEL.2012.051816 Perdana, A., Robb, A., & Wijkstra, M. (2021). From information to choice: A critical inquiry into visualization tools for decision making. IEEE Transactions on Visualization and Computer Graphics, 30 (1), 359–369. https://doi.org/10.1109/TVCG.2023.3282426 Janssen, M., Charalabidis, Y., & Zuiderwijk, A. (2012). Benefits, adoption barriers and myths of open data and open government. Government Information Quarterly, 29 (4), 258–268. https://doi.org/10.1016/j.giq.2015.11.009 Dimara, E., & Stasko, J. (2022). A critical reflection on visualization research: Where do decision-making tasks hide? IEEE Transactions on Visualization and Computer Graphics, 28 (1), 1128–1138. https://doi.org/10.1109/TVCG.2021.3114813 Dimara, E., & Stasko, J. (2022). From information to choice: A critical inquiry into visualization tools for decision making [Data and materials]. OSF. https://osf.io/nrasz/ Huang, M. L., & Nguyen, Q. V. (2012). A survey of visualization for decision making: Data and knowledge visualization. International Journal of Information Technology & Decision Making, 11 (1), 165–188. https://doi.org/10.1142/S0219622012400040 Alhadad, S. S. J. (2018). Visualizing data to support judgement, inference, and decision making in learning analytics: Insights from cognitive psychology and visualization science. Journal of Learning Analytics, 5 (2), 60–85. https://doi.org/10.18608/jla.2018.52.5 Paiva, R. C. F., & Filho, J. A. (2019). Teachers’ perceptions on traditional and non-traditional data visualization for pedagogical decision-making. In Proceedings of the Brazilian Symposium on Computers in Education (SBIE) (pp. 1577–1586). SBC. https://doi.org/10.5753/cbie.sbie.2019.1577 Krist, C. (2017). Data visualization made simple: Insights into becoming visual . New York, NY: Routledge. Sedig, K., & Parsons, P. (2019). Design of visualizations for human-information interaction: A pattern-based framework. Information Visualization, 18 (1), 1–32. https://doi.org/10.1080/10496505.2019.1638264 Khan, A., & Tariq, R. (2018). Big-data-driven safety decision-making: A conceptual framework and its influencing factors. Safety Science, 110 , 411–423. https://doi.org/10.1016/j.ssci.2018.09.014 Wolfert, S., Ge, L., Verdouw, C., & Bogaardt, M. J. (2017). Big data in smart farming–a review. Agricultural systems , 153 , 69-80. https://www.sciencedirect.com/science/article/pii/S0308521X16303754 Gonçalves, A. F. D., Maciel, A. M. A., & Rodrigues, R. L. (2017). Development of a data mining education framework for data visualization in distance learning environments. In International conference on software engineering and knowledge engineering . https://ksiresearch.org/seke/seke17paper/seke17paper_130.pdf Azevedo, R., Millar, G. C., Taub, M., Mudrick, N. V., Bradbury, A. E., & Price, M. J. (2017, March). Using data visualizations to foster emotion regulation during self-regulated learning with advanced learning technologies: a conceptual framework. In Proceedings of the seventh international learning analytics & knowledge conference (pp. 444-448). https://dl.acm.org/doi/abs/10.1145/3027385.3027440 Williamson, W. (2022). Learning analytics dashboards in higher education: A systematic review. Computers & Education, 180 , 104413. https://doi.org/10.1016/j.compedu.2022.104413. Mtjilibe, Tshepang and Rameetse, Emmanuel and Mgwenya, Nkosinathi and Thango, Bonginkosi, Exploring the Challenges and Opportunities of Social Media for Organizational Engagement in SMEs: A Comprehensive Systematic Review (July 06, 2024). Available at SSRN: https://ssrn.com/abstract=4998542 or http://dx.doi.org/10.2139/ssrn.4998542. Khamis, A. Smart Mobility Education and Capacity Building for Sustainable Development: A Review and Case Study. Sustainability 2025, 17(17), 7999; https://doi.org/10.3390/su17177999. Borrego-Ruiz, A.; Borrego, J. Microbial Metabolomes in Alzheimer’s Disease: From Pathogenesis to Therapeutic Potential. Curr. Issues Mol. Biol. 2025, 47(9), 724; https://doi.org/10.3390/cimb47090724. Thango, B. A., & Obokoh, L. (2024). Techno-Economic Analysis of Hybrid Renewable Energy Systems for Power Interruptions: A Systematic Review. Eng, 5(3), 2108-2156. https://doi.org/10.3390/eng5030112. Guo, C.; Xu, S.; Guo, X. Metabolic Engineering of Terpenoid Biosynthesis in Medicinal Plants: From Genomic Insights to Biotechnological Applications. Curr. Issues Mol. Biol. 2025, 47(9), 723; https://doi.org/10.3390/cimb47090723. Tanchangya, T.; Sarker, T.; Rahman, J.; Islam, M.; Islam, N.; Siddiqi, K. Mapping Blockchain Applications in FinTech: A Systematic Review of Eleven Key Domains. Information 2025, 16(9), 769; https://doi.org/10.3390/info16090769. Nethanani, Ronewa and matlombe, luzuko and Vuko, Siphethuxolo N. and Thango, Bonginkosi, Customer Relationship Management (CRM) Systems and their Impact on SMEs Performance: A Systematic Review (October 21, 2024). Available at SSRN: https://ssrn.com/abstract=4996185 or http://dx.doi.org/10.2139/ssrn.4996185. Pachiou, A.; Zervou, E.; Sykaras, N.; Tortopidis, D.; Ioannidis, A.; Jung, R.; Strauss, F.; Kourtis, S. Patient-Reported Outcomes of Digital Versus Conventional Impressions for Implant-Supported Fixed Dental Prostheses: A Systematic Review and Meta-Analysis. J. Pers. Med. 2025, 15(9), 427; https://doi.org/10.3390/jpm15090427. Silva León, P.; Cruz Salinas, L.; Farfán Chilicaus, G.; Castro Ijiri, G.; Chuquitucto Cotrina, L.; Heredia Llatas, F.; Ramos Farroñán, E.; Pérez Nájera, C. Digital Technologies for Young Entrepreneurs in Latin America: A Systematic Review of Educational Innovations (2018–2024). Soc. Sci. 2025, 14(9), 537; https://doi.org/10.3390/socsci14090537. Ngcobo, Kwanele and Bhengu, Sandiswa and Mudau, Ambani and Thango, Bonginkosi and Lerato, Matshaka, Enterprise Data Management: Types, Sources, and Real-Time Applications to Enhance Business Performance - A Systematic Review (September 26, 2024). Systematic Review | September 2024 | DOI: 10.20944/preprints202409.1913.v1, Available at SSRN: https://ssrn.com/abstract=4968451 or http://dx.doi.org/10.2139/ssrn.4968451. Strandberg, P. E., Afzal, W., & Sundmark, D. (2018, October). Decision making and visualizations based on test results. In Proceedings of the 12th ACM/IEEE international symposium on empirical software engineering and measurement (pp. 1-10). https://dl.acm.org/doi/abs/10.1145/3239235.3268921 Bhat, A. S. (2017). Data visualization of requests for information to support construction decision-making (Doctoral dissertation, University of British Columbia). https://open.library.ubc.ca/soa/cIRcle/collections/ubctheses/24/items/1.0344010 Buenaño‐Fernandez, D., Villegas‐CH, W., & Luján‐Mora, S. (2019). The use of tools of data mining to decision making in engineering education—A systematic mapping study. Computer applications in engineering education , 27 (3), 744-758. https://onlinelibrary.wiley.com/doi/abs/10.1002/cae.22100 Zhu, Z., Hoon, H. B., & Teow, K. L. (2017). Interactive data visualization techniques applied to healthcare decision making. In Decision Management: Concepts, Methodologies, Tools, and Applications (pp. 1157-1171). IGI Global Scientific Publishing. https://www.igi-global.com/chapter/interactive-data-visualization-techniques-applied-to-healthcare-decision-making/176799 Janssen, M., & Helbig, N. (2018). Innovating and changing the policy-cycle: Policy-makers be prepared!. Government Information Quarterly , 35 (4), S99-S105. https://www.sciencedirect.com/science/article/abs/pii/S0740624X15300265 Oral, E., Chawla, R., Wijkstra, M., Mahyar, N., & Dimara, E. (2023). From information to choice: A critical inquiry into visualization tools for decision making. IEEE Transactions on Visualization and Computer Graphics , 30 (1), 359-369. https://ieeexplore.ieee.org/abstract/document/10292614 Ak, M. F. (2020, April). A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications. In Healthcare (Vol. 8, No. 2, p. 111). MDPI. https://www.mdpi.com/2227-9032/8/2/111 Dimara, E., & Stasko, J. (2021). A critical reflection on visualization research: Where do decision making tasks hide?. IEEE Transactions on Visualization and Computer Graphics , 28 (1), 1128-1138. https://ieeexplore.ieee.org/abstract/document/9552846 Raineri, P., & Molinari, F. (2021). Innovation in data visualisation for public policy making. In The data shake: opportunities and obstacles for urban policy making (pp. 47-59). Cham: Springer International Publishing. https://library.oapen.org/bitstream/handle/20.500.12657/47327/9783030636937.pdf?sequence=1#page=59 Alhadad, S. S. (2018). Visualizing data to support judgement, inference, and decision making in learning analytics: Insights from cognitive psychology and visualization science. Journal of Learning Analytics , 5 (2), 60-85. https://learning-analytics.info/index.php/JLA/article/view/5815 Hoelscher, J., & Mortimer, A. (2018). Using Tableau to visualize data and drive decision-making. Journal of Accounting Education , 44 , 49-59. https://www.sciencedirect.com/science/article/abs/pii/S0748575117301951 Paiva, R., Bittencourt, I. I., Lemos, W., Vinicius, A., & Dermeval, D. (2018, June). Visualizing learning analytics and educational data mining outputs. In International Conference on Artificial Intelligence in Education (pp. 251-256). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-319-93846-2_46 Bergram, K., & Ochan, B. (2018). Data-driven Biased Decision-making?-Exploring the landscape between dashboards, visualization literacy and decision bias. https://lup.lub.lu.se/student-papers/search/publication/8950609 Huang, L., Wu, C., Wang, B., & Ouyang, Q. (2018). Big-data-driven safety decision-making: a conceptual framework and its influencing factors. Safety science , 109 , 46-56. https://www.sciencedirect.com/science/article/abs/pii/S0925753518300973 Sosulski, K. (2018). Data visualization made simple: insights into becoming visual. Routledge. https://www.taylorfrancis.com/books/mono/10.4324/9781315146096/data-visualization-made-simple-kristen-sosulski Lacefield, W. E., & Applegate, E. B. (2018). Data Visualization in Public Education: Longitudinal Student-, Intervention-, School-, and District-Level Performance Modeling. Online Submission . https://eric.ed.gov/?id=ED582891 Tantalaki, N., Souravlas, S., & Roumeliotis, M. (2019). Data-driven decision making in precision agriculture: The rise of big data in agricultural systems. Journal of agricultural & food information , 20 (4), 344-380. https://www.tandfonline.com/doi/abs/10.1080/10496505.2019.1638264 Al-Kassab, J., Ouertani, Z. M., Schiuma, G., & Neely, A. (2014). Information visualization to support management decisions. International Journal of Information Technology & Decision Making , 13 (02), 407-428. https://www.worldscientific.com/doi/abs/10.1142/S0219622014500497 Manorat, R., Becker, L., & Flory, A. (2019). Global data visualization tools to empower decision-making in nutrition. Sight and Life , 33 (1), 108-114. https://datadent.org/wp-content/uploads/2022/08/SightandLifeMagazine_2019_Data_in_Nutrition_GlobalDataVisualizationTools.pdf Sedrakyan, G., Mannens, E., & Verbert, K. (2019). Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts. Journal of Computer Languages , 50 , 19-38. https://www.sciencedirect.com/science/article/abs/pii/S1045926X18301009 Perdana, A., Robb, A., & Rohde, F. (2019). Interactive data and information visualization: unpacking its characteristics and influencing aspects on decision-making. Pacific Asia Journal of the Association for Information Systems , 11 (4), 4. https://aisel.aisnet.org/pajais/vol11/iss4/4/ Börner, K., Bueckle, A., & Ginda, M. (2019). Data visualization literacy: Definitions, conceptual frameworks, exercises, and assessments. Proceedings of the National Academy of Sciences , 116 (6), 1857-1864. https://www.pnas.org/doi/abs/10.1073/pnas.1807180116 Levy-Fix, G., Kuperman, G. J., & Elhadad, N. (2019). Machine learning and visualization in clinical decision support: current state and future directions. arXiv preprint arXiv:1906.02664 . https://arxiv.org/abs/1906.02664 Aung, T., Niyeha, D., Shagihilu, S., Mpembeni, R., Kaganda, J., Sheffel, A., & Heidkamp, R. (2019). Optimizing data visualization for reproductive, maternal, newborn, child health, and nutrition (RMNCH&N) policymaking: data visualization preferences and interpretation capacity among decision-makers in Tanzania. Global health research and policy , 4 (1), 4. https://link.springer.com/article/10.1186/s41256-019-0095-1 Luo, W. (2019). User choice of interactive data visualization format: The effects of cognitive style and spatial ability. Decision Support Systems , 122 , 113061. https://www.sciencedirect.com/science/article/abs/pii/S0167923619300776 Verma, K., Bhardwaj, S., Arya, R., Islam, M. S. U., Bhushan, M., Kumar, A., & Samant, P. (2019). Latest tools for data mining and machine learning. International Journal of Innovative Technology and Exploring Engineering , 8 (9), 18-23. https://www.researchgate.net/profile/Megha-Bhushan/publication/335455343_Latest_Tools_for_Data_Mining_and_Machine_Learning/links/6762adbf7784cf161e0964a3/Latest-Tools-for-Data-Mining-and-Machine-Learning.pdf Li, Q., Wang, P., Sun, Y., Zhang, Y., & Chen, C. (2019). Data-driven decision making in graduate students’ research topic selection: Cognitive processes and challenging factors. Aslib journal of information management , 71 (5), 657-676. https://www.emerald.com/ajim/article-abstract/71/5/657/38009/Data-driven-decision-making-in-graduate-students?redirectedFrom=fulltext Qu, Z., Zhou, Y., Nguyen, Q. V., & Catchpoole, D. R. (2019, January). Using visualization to illustrate machine learning models for genomic data. In Proceedings of the Australasian computer science week multiconference (pp. 1-8). https://dl.acm.org/doi/abs/10.1145/3290688.3290719 Milligan, J. N. (2019). Learning Tableau 2019: Tools for Business Intelligence, data prep, and visual analytics. Packt Publishing Ltd.https://books.google.co.za/books?hl=en&lr=&id=-jmPDwAAQBAJ&oi=fnd&pg=PP1&dq=Learning+Tableau+2019:+Tools+for+Business+Intelligence,+Data+Prep,+and+ Analysis&ots=MlsRYyEpwf&sig=tOwwi8vyRDxIXF29br7k8ERQGiw&redir_esc=y#v=onepage&q=Learning%20Tableau%202019%3A%20Tools%20for%20 Business%20Intelligence%2C%20Data%20Prep%2C%20and%20Analysis&f=false Stanca, L., Felea, C., Stanca, R., & Pintea, M. (2019, June). The impact of visualization tools on the learning engagement of accounting students. In International Conference in Methodologies and intelligent Systems for Techhnology Enhanced Learning (pp. 148-156). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-030-23884-1_19 Guarese, R., Becker, J., Fensterseifer, H., Walter, M., Freitas, C., Nedel, L., & Maciel, A. (2020, September). Augmented situated visualization for spatial and context-aware decision-making. In Proceedings of the 2020 International Conference on Advanced Visual Interfaces (pp. 1-5). https://dl.acm.org/doi/abs/10.1145/3399715.3399838 Byrd, V. L., & Asunda, P. A. (2020, October). Using evidence based practices and learning to enhance critical thinking skills in students through data visualization. In 2020 IEEE Frontiers in Education Conference (FIE) (pp. 1-9). IEEE. https://ieeexplore.ieee.org/abstract/document/9274157 Redondo, R., Herrero, Á., Corchado, E., & Sedano, J. (2020). A decision-making tool based on exploratory visualization for the automotive industry. Applied Sciences , 10 (12), 4355. https://www.mdpi.com/2076-3417/10/12/4355 Peddoju, S. K., & Upadhyay, H. (2020). Evaluation of IoT data visualization tools and techniques. In Data visualization: Trends and challenges toward multidisciplinary perception (pp. 115-139). Singapore: Springer Singapore. https://link.springer.com/chapter/10.1007/978-981-15-2282-6_7 D'Souza, D. E., Bement, D., & Cory, K. (2022). Cross‐functional integration skills: Are business schools delivering what organizations need?. Decision Sciences Journal of Innovative Education , 20 (3), 117-130. https://onlinelibrary.wiley.com/doi/full/10.1111/dsji.12262 Briggs, T. (2020). Using Data Visualization and Dashboards to Support the Decision Making of Public Library Branch Managers. Wilmington University (Delaware). https://www.proquest.com/openview/1cd402e520032b8a6abe26c2fc10b687/1?pq-origsite=gscholar&cbl=51922&diss=y Cheng, J. C., Chen, W., Chen, K., & Wang, Q. (2020). Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms. Automation in Construction , 112 , 103087. https://www.sciencedirect.com/science/article/abs/pii/S0926580518308562 Rawat, S., Rawat, A., Kumar, D., & Sabitha, A. S. (2021). Application of machine learning and data visualization techniques for decision support in the insurance sector. International Journal of Information Management Data Insights , 1 (2), 100012. https://www.sciencedirect.com/science/article/pii/S2667096821000057 Dimara, E., & Stasko, J. (2021). A critical reflection on visualization research: Where do decision making tasks hide?. IEEE Transactions on Visualization and Computer Graphics , 28 (1), 1128-1138. https://ieeexplore.ieee.org/abstract/document/9552846 Dy, B., Ibrahim, N., Poorthuis, A., & Joyce, S. (2021). Improving visualization design for effective multi-objective decision making. IEEE Transactions on Visualization and Computer Graphics , 28 (10), 3405-3416. https://ieeexplore.ieee.org/abstract/document/9374716 Alshareef, H. N., Majrashi, A., Helal, M., & Tahir, M. (2021). Knowledge extraction and data visualization: a proposed framework for secure decision making using data mining. International Journal of Advanced Computer Science and Applications , 12 (8). https://www.researchgate.net/profile/Muhammad-Tahir-63/publication/354334760_Knowledge_Extraction_and_Data_Visualization_A_Proposed_Framework_for_Secure_ Decision_Making_using_Data_Mining/links/63911644484e65005beec9cc/Knowledge-Extraction-and-Data-Visualization-A-Proposed-Framework-for-Secure-Decision-Making-using-Data-Mining.pdf Talukder, A. K. A., & Deb, K. (2020). PaletteViz: A visualization method for functional understanding of high-dimensional Pareto-optimal data-sets to aid multi-criteria decision making. IEEE Computational Intelligence Magazine , 15 (2), 36-48. https://ieeexplore.ieee.org/abstract/document/9064747 Cepero, T., Montané-Jiménez, L. G., & Toledo-Toledo, G. (2021). Visualization Technologies to Support Decision-Making in City Management. Programming and Computer Software , 47 (8), 803-816. https://link.springer.com/article/10.1134/S0361768821080107 Streeb, D., El-Assady, M., Keim, D. A., & Chen, M. (2021). Why visualize? Arguments for visual support in decision making. IEEE Computer Graphics and Applications , 41 (2), 17-22. https://ieeexplore.ieee.org/abstract/document/9380860 Shee, K., Pal, S. K., Wells, J. C., Ruiz-Morales, J. M., Russell, K., Dudani, S., ... & Odisho, A. Y. (2021). Interactive data visualization tool for patient-centered decision making in kidney cancer. JCO Clinical Cancer Informatics , 5 , 912-920. https://ascopubs.org/doi/full/10.1200/CCI.21.00050 Conejero, J. M., Preciado, J. C., Fernández-García, A. J., Prieto, A. E., & Rodríguez-Echeverría, R. (2021). Towards the use of Data Engineering, Advanced Visualization techniques and Association Rules to support knowledge discovery for public policies. Expert Systems with Applications , 170 , 114509. https://www.sciencedirect.com/science/article/abs/pii/S0957417420311532 Moh'd Ali, M. A., Basahr, A., Rabbani, M. R., & Abdulla, Y. (2020, November). Transforming business decision making with internet of things (IoT) and machine learning (ML). In 2020 International conference on decision aid sciences and application (DASA) (pp. 674-679). IEEE. https://ieeexplore.ieee.org/abstract/document/9317174 Zytek, A., Liu, D., Vaithianathan, R., & Veeramachaneni, K. (2021). Sibyl: Understanding and addressing the usability challenges of machine learning in high-stakes decision making. IEEE Transactions on Visualization and Computer Graphics , 28 (1), 1161-1171. https://ieeexplore.ieee.org/abstract/document/9552849 Yuan, Y. H., Liu, C. H., & Kuang, S. S. (2021). An innovative and interactive teaching model for cultivating talent’s digital literacy in decision making, sustainability, and computational thinking. Sustainability , 13 (9), 5117. https://www.mdpi.com/2071-1050/13/9/5117 Dimara, E., Zhang, H., Tory, M., & Franconeri, S. (2021). The unmet data visualization needs of decision makers within organizations. IEEE Transactions on Visualization and Computer Graphics , 28 (12), 4101-4112. https://ieeexplore.ieee.org/abstract/document/9408391 Cui, Y., Song, X., Hu, Q., Li, Y., Shanthini, A., & Vadivel, T. (2021). Big data visualization using multimodal feedback in education. Computers & Electrical Engineering , 96 , 107544. https://www.sciencedirect.com/science/article/abs/pii/S0045790621004894 Vallet, F., Khouadjia, M., Amrani, A., & Pouzet, J. (2021). Designing a data visualisation and analysis tool for supporting decision-making with public transportation network. Proceedings of the Design Society , 1 , 1093-1102. https://www.cambridge.org/core/journals/proceedings-of-the-design-society/article/designing-a-data-visualisation-and-analysis-tool-for-supporting-decisionmaking-with-public-transportation-network/A5EB2D2288FC7F3DA7610B4A9CB1E945 Sakib, S. N. (2022). Data Visualization in Data Science. https://www.cambridge.org/engage/coe/article-details/626bc5baef2ade3a51419ce1 El-Morr, C., Jammal, M., Ali-Hassan, H., & El-Hallak, W. (2022). Machine Learning for Practical Decision Making. International Series in Operations Research and Management Science . https://link.springer.com/content/pdf/10.1007/978-3-031-16990-8.pdf Marques, B., Santos, B. S., Araújo, T., Martins, N. C., Alves, J. B., & Dias, P. (2019, July). Situated visualization in the decision process through augmented reality. In 2019 23rd international conference information visualisation (IV) (pp. 13-18). IEEE. https://ieeexplore.ieee.org/abstract/document/8811981 Murumba, J. (2022). Learning analytics and educational data visualization in the digital era. Journal of Innovations in Data Science and Big Data Management , 1 (03), 2022. https://www.researchgate.net/profile/Julius-Murumba/publication/359093879_Learning_Analytics_and_Educational_Data_Visualization_in_the_Digital_Era/links/625869dda279ec5dd7f699a8/Learning-Analytics-and-Educational-Data-Visualization-in-the-Digital-Era.pdf Eberhard, K. (2023). The effects of visualization on judgment and decision-making: a systematic literature review. Management Review Quarterly , 73 (1), 167-214. https://link.springer.com/article/10.1007/s11301-021-00235-8 Zheng, M., Pan, X., Bermeo, N. V., Thomas, R. J., Coyle, D., O’hare, G. M., & Campbell, A. G. (2022). Stare: Augmented reality data visualization for explainable decision support in smart environments. IEEE Access , 10 , 29543-29557. https://ieeexplore.ieee.org/abstract/document/9727109 Ak, M. F. (2020, April). A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications. In Healthcare (Vol. 8, No. 2, p. 111). MDPI. https://www.mdpi.com/2227-9032/8/2/111 Pera, A. (2022). The moral decision-making capacity of autonomous mobility technologies: Route planning algorithms, simulation modeling tools, and intelligent traffic monitoring systems. Contemporary Readings in Law and Social Justice , 14 (2), 136-153. https://www.ceeol.com/search/article-detail?id=1085225 Jenkins, T. (2022). Immersive virtual shopping experiences in the retail metaverse: Consumer-driven E-commerce, blockchain-based digital assets, and data visualization tools. Linguistic and Philosophical Investigations , (21), 154-169. https://www.ceeol.com/search/article-detail?id=1045820 Frazão, D. A. G., da Costa, T. S. A., de Araújo, T. D. O., Meiguins, B. S., & dos Santos, C. G. R. (2021, July). A brief review of dashboard visualizations employed to support management or business decisions. In 2021 25th International Conference Information Visualisation (IV) (pp. 100-107). IEEE. https://ieeexplore.ieee.org/abstract/document/9582679 Donohoe, D., & Costello, E. (2020). Data visualisation literacy in higher education: An exploratory study of understanding of a learning dashboard tool. International Journal of Emerging Technologies in Learning (iJET) , 15 (17), 115-126. https://www.learntechlib.org/d/218005/ Bali, S., Gunasekaran, A., Aggarwal, S., Tyagi, B., & Bali, V. (2022). A strategic decision-making framework for sustainable reverse operations. Journal of Cleaner Production , 381 , 135058. https://www.sciencedirect.com/science/article/abs/pii/S0959652622046327 Martynenko, A. A., Tevyashev, A. D., Kulishova, N. Y., & Moroz, B. I. (2022). The problem of automatic classification of pictures using an intelligent decision-making system based on the knowledge graph and fine-grained image analysis. https://ela.kpi.ua/items/6fa67074-ad49-4d45-bf91-9a45ecb9d17b Kamissoko, D., Gourc, D., Marmier, F., & Clement, A. (2022). A Go/No-Go Decision-Making Model Based on Risk and Multi-Criteria Techniques for Project Selection. International Journal of Decision Support System Technology (IJDSST) , 15 (2), 1-21. https://www.igi-global.com/article/a-gono-go-decision-making-model-based-on-risk-and-multi-criteria-techniques-for-project-selection/315641 Ren, Y., Song, J., Wang, L., Lu, W., & Wang, X. (2022). Research on Lane-Changing Decision-Making Behavior of Intelligent Network-Connected Autonomous Vehicles (No. 2022-01-7066). SAE Technical Paper. https://www.sae.org/publications/technical-papers/content/2022-01-7066/ Zhang, X., Zhou, D., Zhou, G., Cao, W., Wang, M., Wang, C., & Li, H. (2022, December). Research on auxiliary decision-making of power grid fault recovery based on generative adversarial imitation learning. In Proceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial Intelligence (pp. 1140-1145). https://dl.acm.org/doi/abs/10.1145/3584376.3584578 Pazouki, P., Teshnizi, E. S., Bertone, E., Helfer, F., & Stewart, R. A. (2022). Multi-criteria decision making for a holistic assessment of sustainable alternatives in SWRO desalination: A case study. Desalination , 544 , 116127. https://www.sciencedirect.com/science/article/abs/pii/S0011916422005823 Diao, F., & Wei, G. (2022). EDAS method for multiple attribute group decision making under spherical fuzzy environment. International Journal of Knowledge-based and Intelligent Engineering Systems , 26 (3), 175-188. https://journals.sagepub.com/doi/abs/10.3233/KES-220018 Ali, L., Asadi, M., Gašević, D., Jovanović, J., & Hatala, M. (2013). Factors influencing beliefs for adoption of a learning analytics tool: An empirical study. Computers & Education , 62 , 130-148. https://www.sciencedirect.com/science/article/abs/pii/S0360131512002515 Llaha, O., Aliu, A., & Kadena, E. (2023). Application of clustering methods and data visualization for decision making in higher education. Journal of Awareness , 8 (3), 297-303. https://www.ceeol.com/search/article-detail?id=1205063 Ardabili, B. R., Yao, S., Pazho, A. D., Bourque, L., & Tabkhi, H. (2023). Enhancing situational awareness in surveillance: Leveraging data visualization techniques for machine learning-based video analytics outcomes. arXiv preprint arXiv:2312.05629 . https://arxiv.org/abs/2312.05629 Kharakhash, О. (2023). Data visualization: transforming complex data into actionable insights. Automation of technological and business processes , 15 (2), 4-12. https://journals.ontu.edu.ua/index.php/atbp/article/view/2520 Prem, E. (2023). From ethical AI frameworks to tools: a review of approaches. AI and Ethics , 3 (3), 699-716. https://link.springer.com/article/10.1007/s43681-023-00258-9 Yalim, C., & Handley, H. A. (2023). The effectiveness of visualization techniques for supporting decision-making. https://digitalcommons.odu.edu/msvcapstone/2023/datascience/1/ Pala, S. K. (2017). Advance Analytics for Reporting and Creating Dashboards with Tools like SSIS, Visual Analytics and Tableau. International Journal of Open Publication and Exploration , 5 (2), 3006-2853. https://www.researchgate.net/profile/Sravan-Pala/publication/378679002_Advance_Analytics_for_ Reporting_and_Creating_Dashboards_with_Tools_like_SSIS_Visual_Analytics_and_Tableau/links/65e366bfc3b52a117006c436/Advance-Analytics-for-Reporting-and-Creating-Dashboards-with-Tools-like-SSIS-Visual-Analytics-and-Tableau.pdf Stanca, L., Felea, C., Stanca, R., & Pintea, M. (2020, June). The impact of personality, attitude and visual decision-making dashboard tools on the learning engagement of economist students. In International Conference in Methodologies and intelligent Systems for Techhnology Enhanced Learning (pp. 106-116). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-030-52538-5_12 Nasir, F., Ahmed, A. A., Kiraz, M. S., Yevseyeva, I., & Saif, M. (2024). Data-Driven Decision-Making for Bank Target Marketing Using Supervised Learning Classifiers on Imbalanced Big Data. Computers, Materials & Continua , 81 (1). https://openurl.ebsco.com/EPDB%3Agcd%3A2%3A1405570/detailv2?sid=ebsco%3Aplink%3Ascholar&id=ebsco%3Agcd%3A180260329&crl=c&link_origin=scholar.google.com Taylor, L., Gupta, V., & Jung, K. (2024). Leveraging visualization and machine learning techniques in education: a case study of k-12 state assessment data. Multimodal Technologies and Interaction , 8 (4), 28. https://www.mdpi.com/2414-4088/8/4/28 Phang, Z. B., Haw, S. C., Tai, T. E., & Ng, K. W. (2024, September). Interactive Data Visualization to Optimize Decision-Making Process. In 2024 International Symposium on Parallel Computing and Distributed Systems (PCDS) (pp. 1-6). IEEE. https://ieeexplore.ieee.org/abstract/document/10743427 Ouyang, W. (2024). Data visualization in big data analysis: Applications and future trends. Journal of Computer and Communications , 12 (11), 76-85. Shahidan, N. F. A., Ibrahim, A. F., & Jamaluddin, M. N. F. (2024). Data Visualization of Student Academic Performance Analysis. Applied Mathematics and Computational Intelligence (AMCI) , 13 (4), 49-61. https://ejournal.unimap.edu.my/index.php/amci/article/view/1476 Oral, E., Chawla, R., Wijkstra, M., Mahyar, N., & Dimara, E. (2023). From information to choice: A critical inquiry into visualization tools for decision making. IEEE Transactions on Visualization and Computer Graphics , 30 (1), 359-369. https://ieeexplore.ieee.org/abstract/document/10292614 Shinde, B. G., & Shivthare, S. (2024). Impact of data visualization in data analysis to improve the efficiency of machine learning models. Journal of Advanced Zoology , 45 , 107-112. https://shorturl.at/JGnD8 Hossain, Q., Yasmin, F., Biswas, T. R., & Asha, N. B. (2024). Data-Driven Business Strategies: A Comparative Analysis of Data Science Techniques in Decision-Making. Sch J Econ Bus Manag , 9 , 257-263. https://www.saspublishers.com/media/articles/SJEBM_119_257-263.pdf Uddin, M. K. S. (2024). A review of utilizing natural language processing and AI for advanced data visualization in real-time analytics. Global Mainstream Journal , 1 (4), 10-62304. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4993556 Shahidan, N. F. A., Ibrahim, A. F., & Jamaluddin, M. N. F. (2024). Data Visualization of Student Academic Performance Analysis. Applied Mathematics and Computational Intelligence (AMCI) , 13 (4), 49-61. https://ejournal.unimap.edu.my/index.php/amci/article/view/1476 O’Shaughnessy, M., Glover, J., Hafizi, R., Barhi, M., Clowes, R., Chong, S. Y., ... & Cooper, A. I. (2024). Porous isoreticular non-metal organic frameworks. Nature , 630 (8015), 102-108. https://www.nature.com/articles/s41586-024-07353-9 Bach, B., Keck, M., Rajabiyazdi, F., Losev, T., Meirelles, I., Dykes, J., ... & Carpendale, S. (2023). Challenges and opportunities in data visualization education: A call to action. IEEE Transactions on visualization and computer graphics , 30 (1), 649-660. https://ieeexplore.ieee.org/abstract/document/10310184 Chen, T., Liu, Y. X., Chen, T., Yang, M., Fan, S., Shi, M., ... & Huang, L. (2024). ImageGP 2 for enhanced data visualization and reproducible analysis in biomedical research. Imeta , 3 (5), e239. https://onlinelibrary.wiley.com/doi/full/10.1002/imt2.239 Sotiropoulos, C., Giormezis, N., Pertsas, V., & Tsirkas, T. (2024). Biomarkers and data visualization of insulin resistance and metabolic syndrome: an applicable approach. Life , 14 (9), 1197. https://www.mdpi.com/2075-1729/14/9/1197 Zheng, M., Lillis, D., & Campbell, A. G. (2024). Current state of the art and future directions: Augmented reality data visualization to support decision-making. Visual Informatics , 8 (2), 80-105. https://www.sciencedirect.com/science/article/pii/S2468502X24000202 Romero-Organvidez, D., Horcas, J. M., Galindo, J. A., & Benavides, D. (2024). Data visualization guidance using a software product line approach. Journal of Systems and Software , 213 , 112029. https://www.sciencedirect.com/science/article/pii/S0164121224000724 Yin, W., Hu, Q., Liu, W., Liu, J., He, P., Zhu, D., & Kornejady, A. (2024). Harnessing Game Engines and Digital Twins: Advancing Flood Education, Data Visualization, and Interactive Monitoring for Enhanced Hydrological Understanding. Water , 16 (17), 2528. https://www.mdpi.com/2073-4441/16/17/2528 Mehrotra, S., Rangaiah, B., & Kathi, S. (2022). Relationship between decision-making, time perspective and stress. Timing & Time Perception , 12 (1), 47-63. https://brill.com/view/journals/time/12/1/article-p47_005.xml Then, S. N., & Bigby, C. (2024). Supported decision-making and the Disability Royal Commission. Research and Practice in Intellectual and Developmental Disabilities , 11 (1), 86-106. https://www.tandfonline.com/doi/full/10.1080/23297018.2024.2330961 Aluja, A., Balada, F., García, O., & García, L. F. (2024). Psychometric study of two decision-making measures: The melbourne decision-making questionnaire versus the general decision-making style questionnaire. Psychiatry International , 5 (3), 503-514. https://www.mdpi.com/2673-5318/5/3/36 D’Alessio, I., Aitella, U., Giannini, A. M., & Burrai, J. (2024). “What about Military Decision-Making?”: A Bibliometric Review of Published Articles. Behavioral Sciences , 14 (7), 514. https://www.mdpi.com/2076-328X/14/7/514 Sun, H. Y., Xiao, Y. T., & Yang, S. S. (2024). The group intertemporal decision-making process. Behavioral Sciences , 14 (9), 815. https://www.mdpi.com/2076-328X/14/9/815 Karcılı, I., & Sevim, S. (2024). The effect of argumentation-based sociobiological topic teaching on 7th grade students' argumentation levels, decision-making skills and decision-making styles. Pamukkale Universitesi Egitim Fakultesi Dergisi-Pamukkale University Journal of Education . https://gcris.pau.edu.tr/bitstream/11499/57389/1/10.9779-pauefd.1435514-3722431.pdf Kollar, J. (2024). Decision-making on the job choice in the condition of Slovak households. https://naos-be.zcu.cz/server/api/core/bitstreams/5b1ec474-441d-4f5b-83f4-75e80823d41e/content Zaheer, R., Hanif, M. K., Sarwar, M. U., & Talib, R. (2025). Evaluating the Effectiveness of Dimensionality Reduction on Machine Learning Algorithms in Time Series Forecasting. IEEE Access . https://ieeexplore.ieee.org/abstract/document/10929010 Pham, D. L., Gillette, A. A., Riendeau, J., Wiech, K., Guzman, E. C., Datta, R., & Skala, M. C. (2025). Perspectives on label-free microscopy of heterogeneous and dynamic biological systems. Journal of Biomedical Optics , 29 (S2), S22702-S22702. https://www.spiedigitallibrary.org/journals/journal-of-biomedical-optics/volume-29/issue-S2/S22702/Perspectives-on-label-free-microscopy-of-heterogeneous-and-dynamic-biological/10.1117/1.JBO.29.S2.S22702.short Grolli, R. E., Fabrizzio, G. C., Cabral, E. C., de Souza, J. M., de Souza Vieira, L., Zambeli, A. S., ... & Zibetti, A. W. (2025). Predictive tools in intensive care unit management: a protocol of a scoping review. Journal of Medical Artificial Intelligence , 8 . https://jmai.amegroups.org/article/view/9771/html Sharma, R. M. (2025). Artificial intelligence in medical image analysis and molecular diagnostics: recent advances and applications. Journal of Medical Artificial Intelligence , 8 . https://jmai.amegroups.org/article/view/10103/html Shah, R., Ali, S., Raziq, F., Ali, S., Ismail, P. M., Shah, S., ... & Qiao, L. (2023). Exploration of metal organic frameworks and covalent organic frameworks for energy-related applications. Coordination Chemistry Reviews , 477 , 214968. https://www.sciencedirect.com/science/article/abs/pii/S001085452200563X Mildau, K., Ehlers, H., Meisenburg, M., Del Pup, E., Koetsier, R. A., Ortega, L. R. T., ... & van der Hooft, J. J. (2025). Effective data visualization strategies in untargeted metabolomics. Natural Product Reports , 42 (6), 982-1019. https://pubs.rsc.org/en/content/articlehtml/2024/np/d4np00039k Chauhan, M., & Shiaeles, S. (2023). An analysis of cloud security frameworks, problems and proposed solutions. Network , 3 (3), 422-450. https://www.mdpi.com/2673-8732/3/3/18 Bruch, E., & Feinberg, F. (2017). Decision-making processes in social contexts. Annual review of sociology , 43 (1), 207-227. https://www.annualreviews.org/content/journals/10.1146/annurev-soc-060116-053622 Bajracharya, S., Carenini, G., Chamberlain, B., Chen, K., Klein, D., Poole, D., ... & Öberg, G. (2018). Interactive visualization for group decision analysis. International Journal of Information Technology & Decision Making , 17 (06), 1839-1864. https://www.worldscientific.com/doi/abs/10.1142/S0219622018500384 Padilla, L. M., Creem-Regehr, S. H., Hegarty, M., & Stefanucci, J. K. (2018). Decision making with visualizations: a cognitive framework across disciplines. Cognitive research: principles and implications , 3 (1), 29. https://link.springer.com/article/10.1186/s41235-018-0120-9 Burnay, C., Dargam, F., & Zarate, P. (2019). Data visualization for decision-making: an important issue. Operational Research , 19 (4), 853-855. https://link.springer.com/article/10.1007/s12351-019-00530-z Cohen, D. J., Wyte-Lake, T., Canfield, S. M., Hall, J. D., Steege, L., Wareg, N. K., & Koopman, R. J. (2022). Impact of home blood pressure data visualization on hypertension medical decision making in primary care. The Annals of Family Medicine , 20 (4), 305-311. https://www.annfammed.org/content/20/4/305?2023/7/20/?2023/7/20/ Echeverria, V., Martinez-Maldonado, R., Shum, S. B., Chiluiza, K., Granda, R., & Conati, C. (2018). Exploratory versus explanatory visual learning analytics: Driving teachers’ attention through educational data storytelling. Journal of Learning Analytics , 5 (3), 73-97. https://research.monash.edu/en/publications/exploratory-versus-explanatory-visual-learning-analytics-driving- Liu, S., Miao, H., Li, Z., Olson, M., Pascucci, V., & Bremer, P. T. (2024, June). AVA: towards autonomous visualization agents through visual perception‐driven decision‐making. In Computer Graphics Forum (Vol. 43, No. 3, p. e15093). https://onlinelibrary.wiley.com/doi/abs/10.1111/cgf.15093 Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7560670","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":511671674,"identity":"9d747492-fff1-44b3-9b8a-26e00fcca371","order_by":0,"name":"Maselesele Jacob","email":"data:image/png;base64,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","orcid":"","institution":"University of Johannesburg","correspondingAuthor":true,"prefix":"","firstName":"Maselesele","middleName":"","lastName":"Jacob","suffix":""},{"id":511671675,"identity":"e8ef2dd0-0f6d-401c-8185-cd7aa632e05a","order_by":1,"name":"Magara P. Tshedza","email":"","orcid":"","institution":"University of Johannesburg","correspondingAuthor":false,"prefix":"","firstName":"Magara","middleName":"P.","lastName":"Tshedza","suffix":""},{"id":511671676,"identity":"608d4914-035a-4276-8c31-527a71d93636","order_by":2,"name":"Mukwevho Hulisani","email":"","orcid":"","institution":"University of Johannesburg","correspondingAuthor":false,"prefix":"","firstName":"Mukwevho","middleName":"","lastName":"Hulisani","suffix":""}],"badges":[],"createdAt":"2025-09-08 06:37:07","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-7560670/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7560670/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90861413,"identity":"bb18c921-4b1f-4f52-bad2-d34a2013f84b","added_by":"auto","created_at":"2025-09-09 06:15:10","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":466586,"visible":true,"origin":"","legend":"\u003cp\u003eBibliometric Analysis of Study Search Keywords: (a) Overlay Visualization. (b) Network Visualization. (c) Density Visualization.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/3d88bba22c1085317b1015c6.png"},{"id":90861412,"identity":"b130417c-e22a-4871-94c4-fcf419d30fad","added_by":"auto","created_at":"2025-09-09 06:15:10","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":99292,"visible":true,"origin":"","legend":"\u003cp\u003eProcedures and Stages of the Review.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/7e4cbc69e22ffb57b144ab5f.png"},{"id":90859613,"identity":"ce191a21-34b6-4e01-aaf1-c7f7d0bfc339","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":128412,"visible":true,"origin":"","legend":"\u003cp\u003eFlow of Data Selection and Extraction.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/7f28eb17a8f3ddc973112e9b.png"},{"id":90861777,"identity":"84536aed-650e-4376-955b-98ae6e2c865c","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":150720,"visible":true,"origin":"","legend":"\u003cp\u003eRisk of Bias Assessment Process for Non-Randomized Studies.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/0fa8b46f5e6b27ab04cb64ae.png"},{"id":90859616,"identity":"137b6166-346f-49bc-8b36-595e7d02e733","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":108271,"visible":true,"origin":"","legend":"\u003cp\u003eSystematic Review Process for Data Visualization Tools and Techniques in Education and Machine Learning.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/72ac9d7d55c088ad98e1ea8c.png"},{"id":90862579,"identity":"560214cc-3bcc-4690-afa6-e24721ebaa21","added_by":"auto","created_at":"2025-09-09 06:31:10","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":116005,"visible":true,"origin":"","legend":"\u003cp\u003eProposed PRISMA Flowchart\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/dfd6a906cd6da2b0e332572f.png"},{"id":90861778,"identity":"52ffa2c8-c79d-434d-8bc7-bca5d261391b","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":26499,"visible":true,"origin":"","legend":"\u003cp\u003eResearch Distribution by Published Works.\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/754e64e294591437350cb6ca.png"},{"id":90859673,"identity":"c403f995-6ae8-4e08-b5ce-2c0c3861a0fb","added_by":"auto","created_at":"2025-09-09 06:07:11","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":199097,"visible":true,"origin":"","legend":"\u003cp\u003eCountry Distribution of Reviewed Papers.\u003c/p\u003e","description":"","filename":"8.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/1374a3592a0de641158bc042.png"},{"id":90859619,"identity":"5af5b061-3d35-4efa-a01e-15cb66cc6b78","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":30450,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of Publications.\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/50d872559a41738255de572b.png"},{"id":90861783,"identity":"8a2aabd9-0afb-4352-b9b7-be6b684f0dc4","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":83396,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of Databases Used.\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/9d03851ae10475435feec60e.png"},{"id":90861784,"identity":"7fc00967-8096-4f4f-a2a5-da5ec7eeffca","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":131949,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of Visualization Tools.\u003c/p\u003e","description":"","filename":"11.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/cf1788f9627c0b257957a982.png"},{"id":90861781,"identity":"494dc3e1-6781-4a5c-8a80-5469504be3af","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":180369,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of Visualization Techniques.\u003c/p\u003e","description":"","filename":"12.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/48f209690165dea69f9677fd.png"},{"id":90859637,"identity":"5e8e56fa-ef87-4335-87cc-5a84024ba289","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":55449,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of Application Domains.\u003c/p\u003e","description":"","filename":"13.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/c913a8b9a8947e586b2c9983.png"},{"id":90861424,"identity":"1bdc98fc-761c-42be-bb0a-643007fc7bd0","added_by":"auto","created_at":"2025-09-09 06:15:10","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":107078,"visible":true,"origin":"","legend":"\u003cp\u003eDecision-Making Outcomes.\u003c/p\u003e","description":"","filename":"14.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/62e5ed71469bbd5a4d9948a8.png"},{"id":90861782,"identity":"d29e7883-5ead-4703-9e29-88cdbc9b4d99","added_by":"auto","created_at":"2025-09-09 06:23:10","extension":"png","order_by":15,"title":"Figure 15","display":"","copyAsset":false,"role":"figure","size":55969,"visible":true,"origin":"","legend":"\u003cp\u003eOutcomes on Cognitive Load.\u003c/p\u003e","description":"","filename":"15.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/aded1b9bb22d3aace05999c3.png"},{"id":90859644,"identity":"4f755005-5261-4b04-a4b1-600b5bd77a80","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":16,"title":"Figure 16","display":"","copyAsset":false,"role":"figure","size":130136,"visible":true,"origin":"","legend":"\u003cp\u003eUser Groups.\u003c/p\u003e","description":"","filename":"16.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/bcf7b8e44617ed26c82f98a4.png"},{"id":90859641,"identity":"b64f24c2-1585-4e6d-a2f3-2f1f352a4c1e","added_by":"auto","created_at":"2025-09-09 06:07:10","extension":"png","order_by":17,"title":"Figure 17","display":"","copyAsset":false,"role":"figure","size":141271,"visible":true,"origin":"","legend":"\u003cp\u003eChallenges \u0026amp; Limitations.\u003c/p\u003e","description":"","filename":"17.png","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/e2cfa6574480824796091365.png"},{"id":91148810,"identity":"66bf7c03-1df4-4433-b8b7-a11fb698be2a","added_by":"auto","created_at":"2025-09-12 06:45:46","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3900117,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7560670/v1/18f066c2-1065-4dc3-9a05-12d205dde13b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTools, Techniques, and Applications of Data Visualization in Education and Machine Learning\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn today\u0026rsquo;s data-driven environment, the integration of visualization and analytical tools has profoundly transformed organizational and educational practices by enabling the interpretation of complex datasets, the extraction of actionable insights, and the support of informed decision-making, ultimately fostering innovation and competitive advantage.In the context of education and learning, visualization techniques have become essential in transforming raw educational data into meaningful insights, enabling educators and learners to make evidence-based decisions that enhance both teaching practices and learning outcomes (Buena\u0026ntilde;o-Fernandez et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Paiva et al., 2019; J\u0026auml;rvel\u0026auml; et al., 2017). Recent studies highlight the transformative impact of data visualization and mining techniques across diverse domains, with applications ranging from optimizing educational processes and supporting pedagogical decision-making to enhancing learners\u0026rsquo; self-regulation and engagement in technology-enhanced environments (J\u0026auml;rvel\u0026auml; et al., 2017; Paiva et al., 2019). Recent research highlights the transformative impact of data visualization and data mining techniques across educational and learning contexts. Visualization tools have been instrumental in supporting educators and learners to interpret complex datasets, monitor performance, and make evidence-based decisions that enhance learning outcomes (Bergram \u0026amp; Ochan, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). Despite these advancements, there remains a gap in understanding the comprehensive application of these technologies within resource-constrained learning environments or emerging educational systems (Paiva et al.2019). Smaller institutions and programs, which often face limitations in data infrastructure and analytic expertise, require tailored approaches to leverage visualization and mining techniques effectively for decision-making. However, most existing literature has focused on well-resourced or large-scale educational settings, leaving smaller contexts underexplored (Anderson, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Recent research emphasizes the transformative role of data visualization and data mining in enhancing decision-making across educational and learning contexts. Visualization tools have been applied to support learners\u0026rsquo; self-regulation, improve comprehension of complex datasets, and guide evidence-based pedagogical decisions (J\u0026auml;rvel\u0026auml; et al., 2017; Paiva et al., 2019; Krist, 2019; Milligan, \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Data mining techniques have been explored for their ability to extract actionable insights from educational data, such as predicting student performance, identifying knowledge gaps, and informing curriculum design (Buena\u0026ntilde;o-Fernandez et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Anderson, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Murumba et al., 2023). Despite these developments, a gap remains in understanding how these technologies function comprehensively in resource-constrained or emerging educational settings, particularly with smaller institutions and programs that face limitations in analytics expertise (Paiva et al., 2019; Perdana et al., 2023; Milligan, \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Most studies have focused on well-resourced or large-scale learning environments, leaving underexplored contexts without guidance on effective implementation of visualization and mining tools for decision-making (Krist, 2019; Anderson, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; J\u0026auml;rvel\u0026auml; et al., 2017).\u003c/p\u003e\u003cp\u003eThe increasing complexity of educational environments and the rapid evolution of learning technologies have highlighted the need for effective data-driven decision-making to improve learning outcomes (Buena\u0026ntilde;o-Fernandez et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; J\u0026auml;rvel\u0026auml; et al., 2017; Paiva et al., 2019). Research has examined various approaches for applying data visualization and mining techniques in education, including the use of interactive dashboards, learning analytics platforms, and advanced visualization tools to support both teachers and learners in monitoring progress and guiding instructional strategies (Janssen \u0026amp; Helbig, 2017). Despite these advances, challenges remain in fully integrating these technologies, particularly in resource-constrained or emerging educational settings where expertise and infrastructure may be limited (Perdana et al., 2023; Anderson, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Prior studies have explored the design, implementation, and evaluation of visual analytics systems across diverse learning contexts, highlighting both successful applications and persistent barriers to adoption (J\u0026auml;rvel\u0026auml; et al., 2017; Paiva et al., 2019; Milligan, \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). This systematic review seeks to synthesize a decade of research on data visualization and learning analytics, identifying key trends, challenges, and opportunities associated with these technologies. By analyzing studies published over this period, the review aims to provide actionable insights for educators, instructional designers, and policymakers, ultimately enhancing evidence-based decision-making and learning outcomes. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e presents a comparative analysis of existing review works and the focus of this study, emphasizing its distinct contribution in exploring the applications and impact of data visualization and mining techniques in educational contexts. Uncovering patterns in technological adoption, showcasing effective case studies, and discussing practical implications, this review aims to establish a foundation for future research and informed educational practice (Murumba et al., 2023).\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparative Analysis of Existing Review Works and the Proposed Systematic Review on the Applications and Impact of Data Visualization and Learning Analytics on Educational Decision-Making.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRef.\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eContribution\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePros\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eCons\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePerdana, A., Robb, A., \u0026amp; et al. (2021).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExplores interactive data visualization techniques for enhancing decision-making in education.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDemonstrates how interactive visualizations improve comprehension and engagement.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited focus on real-time or adaptive learning environments.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMilligan, J. N. (2019)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDemonstrates practical use of Tableau for visualizing educational data to support decision-making.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProvides hands-on guidance for educators and analysts; practical tool implementation.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFocused mainly on Tableau; less coverage of other visualization platforms.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKrist, B. (2018).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eInvestigates foundational visualization techniques for interpreting complex educational datasets.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSimple, clear methods that improve data literacy and interpretation.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited empirical evaluation in educational contexts.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePaiva, A., et al. (2020).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExamine educators\u0026rsquo; perceptions of different visualization tools for teaching decisions.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHighlights teacher preferences and practical applicability.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSample size and regional focus may limit generalization.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMurumba, J., et al. (2022).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eReviews learning analytics dashboards and visualization frameworks in digital learning environments.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eComprehensive coverage of visualization dashboards and educational insights.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited focus on small-scale classroom adoption.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAnderson, T. (2019).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eShows practical integration of personal analytics and visualizations for educational decision-making.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eClear framework for educators and students to leverage data for learning improvements.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFocused on individual projects; less about institutional-wide implementation.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eChatti, M. A., Muslim, A., \u0026amp; Th\u0026uuml;s, H. (2012)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIntroduces a comprehensive reference model for learning analytics.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProvides a structured framework for understanding learning analytics.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLacks empirical validation; theoretical in nature.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFerguson, R. (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2012\u003c/span\u003e).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDiscusses the drivers, developments, and challenges in learning analytics.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eOffers insights into the evolving landscape of learning analytics.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited focus on practical applications; more theoretical.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSiemens, G., \u0026amp; Long, P. (2011).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExplores the role of analytics in learning and education\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHighlights the potential of analytics in enhancing educational outcomes.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBrief overview; lacks in-depth analysis.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRomero, C., \u0026amp; Ventura, S. (2010).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eReviews the state of the art in educational data visualization.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProvides a comprehensive overview of educational data visualization techniques.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFocuses primarily on data tools; less on visualization.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePaiva, A., et al. (2020)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eInvestigates teachers' perceptions of data visualization tools.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eOffers practical insights into educators' views on data visualization.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited sample size; region-specific findings.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWilliamson, W. (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). 2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eReviews research on learning analytics dashboards in higher education\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProvides a comprehensive analysis of dashboard research.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFocuses mainly on higher education; less on K-12\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProposed systematic review\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSynthesizes studies (2015\u0026ndash;2025) on data visualization and learning analytics in education\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eComprehensive: covers visualization types, analytic methods, teacher/student perspectives, and learning outcomes.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLimited by exclusion of gray literature and non-English studies.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eDespite the growing body of research on DV and LA, several gaps remain that limit their effective application in education and machine learning. Most existing reviews emphasize higher education, while K\u0026ndash;12 and small-scale classroom environments remain underexplored. This gap overlooks unique challenges such as limited infrastructure, teacher training needs, and resource constraints, which are critical for equitable adoption of visualization and analytics. Many studies focus either on visualization tools and techniques or on learning analytics frameworks, but rarely on their integrated impact. As a result, there is insufficient understanding of how DV and LA together can enhance pedagogy, institutional decision-making, and student outcomes. The majority of prior work relies on short-term, cross-sectional data, which restricts insight into the long-term effects of visualization and analytics on teaching quality and institutional performance. Few studies employ longitudinal or mixed-method approaches that can capture evolving adoption patterns and sustained impact. While technical efficiency and tool implementation are well-studied, less attention is given to teacher engagement, institutional culture, and decision-making processes that shape adoption. These factors are crucial for bridging the gap between technical capacity and practical educational impact. Existing reviews often have limited regional scope or small sample sizes, and several exclude non-English studies or gray literature, constraining global relevance and inclusivity. This creates a bias toward Western, higher-education contexts while neglecting diverse cultural and systemic realities.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec2\" class=\"Section2\"\u003e\u003ch2\u003e1.1. Research questions\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThis study investigates the applications and impact of DV and LA in supporting educational decision-making. To guide the review, the following research questions were addressed:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eHow has research on DV and LA evolved over time, and what trends characterize publication activity across years and publication outlets?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eWhich countries and regions contribute most to DV and LA research, and what does this reveal about global participation and collaboration?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eWhich databases, tools, and visualization techniques are most frequently used in DV and LA research, and why do dashboards and descriptive methods dominate over advanced techniques?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eIn which application domains are DV and LA most commonly applied, and how do these domains shape outcomes of decision-making?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eHow does visualization affect cognitive load in educational decision-making, and what strategies are employed to balance simplicity, complexity, and interpretability?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eWho are the primary user groups of DV and LA systems, and how do their roles and needs influence the design and adoption of these tools?\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eWhat challenges and limitations are most frequently reported in DV and LA research, and how do these constrain adoption, methodological transparency, and scalability?\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e1.2. Hypotheses Development\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eBuilding upon the research questions, the following hypotheses are proposed to explore the applications and advantages of DV and LA systems in supporting educational decision-making. These hypotheses examine how publication patterns, geographical concentration, visualization methods, cognitive load, and user diversity influence adoption and effectiveness:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH1\u003c/b\u003e: Research on DV and LA has grown steadily between 2017\u0026ndash;2024 with peaks in later years, suggesting increasing attention to visualization-supported decision-making, though unevenly distributed across time.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH2\u003c/b\u003e: DV and LA research is disproportionately concentrated in a few countries (USA, China, India), leaving limited representation from emerging or under-resourced regions.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH3\u003c/b\u003e: Dependence on Google Scholar, Scopus, and Web of Science, and the frequent use of Tableau, Power BI, and Excel, reflects accessibility and institutional familiarity, while advanced techniques remain underutilized.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH4\u003c/b\u003e: Dashboards, bar graphs, and line graphs dominate due to their clarity and scalability, while advanced visualizations are underreported.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH5\u003c/b\u003e: Education and business are the most represented domains, producing decision-making outcomes concentrated in business/industry, policy, and healthcare.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH6\u003c/b\u003e: Visualization design strongly influences cognitive load, with evidence split between reduction strategies (25%) and overload risks (20%), highlighting trade-offs in clarity vs. complexity.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH7\u003c/b\u003e: Analysts, managers, and researchers/students dominate as primary users (Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e16\u003c/span\u003e), while citizens and healthcare practitioners are underrepresented, suggesting unequal benefits across user categories.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eH8\u003c/b\u003e: Persistent barriers such as complexity, scalability, interpretability, and integration challenges (Fig.\u0026nbsp;\u003cspan refid=\"Fig16\" class=\"InternalRef\"\u003e17\u003c/span\u003e) constrain adoption and methodological transparency.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e1.3. Rationale\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe rationale for this review is to systematically examine the state of DV and LA in educational decision-making, emphasizing how geographic, institutional, and socio-economic contexts shape adoption and outcomes. Given the reliance on data-informed practices in education, it is essential to evaluate how visualization techniques and LA systems support teaching effectiveness, learning outcomes, and institutional performance. This study addresses a gap by focusing on publications between 2015\u0026ndash;2025, synthesizing evidence to identify trends, highlight methodological gaps, and propose strategies for advancing the role of DV and LA in diverse educational contexts.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e1.4. Objectives\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe primary objective of this review is to synthesize research on DV and LA applications in education, identifying the most common tools, techniques, and domains, and analyzing their impact on decision-making outcomes. Specific objectives are to:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eExamine publication and geographical trends.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eIdentify dominant tools, techniques, and databases.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAssess application domains and their decision-making contributions.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eEvaluate the impact of visualization design on cognitive load.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eMap the diversity of user groups benefiting from DV and LA.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eSynthesize recurring challenges and limitations constraining adoption.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e1.5. Research Contributions\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThis review contributes to the literature by:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eProviding a comprehensive synthesis of DV and LA studies (2015\u0026ndash;2025) across education and related domains.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eHighlighting imbalances in publication trends, geographical representation, and visualization methods.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eMapping outcomes on decision-making, cognitive load, and user adoption.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eIdentifying methodological, technical, and contextual gaps that constrain scalability and inclusivity.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eProposing a framework integrating inputs, context, methods, mechanisms, users, and boundaries for advancing DV and LA adoption.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e1.6. Research Novelty\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eTo the best of the authors\u0026rsquo; knowledge, this is the first review to exclusively integrate DV and LA studies in education with a focus on decision-making outcomes. The novelty lies in:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eA holistic evaluation of visualization tools, techniques, domains, and user groups, emphasizing their role in improving evidence-based teaching, learning, and institutional decision-making.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eIntroducing an integrative framework that connects visualization methods, learning analytics processes, and decision outcomes, offering predictive insights for improving adoption and effectiveness in education.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":" 2. Materials and Methods","content":"\u003cdiv class=\"Heading\"\u003e\u003cem\u003e2.\u003c/em\u003e Materials and Methods\u003c/div\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn this subsection, the study presents the methodology used to conduct a systematic review on the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning. The review covers literature published between 2015 and 2025. To the best of the authors\u0026rsquo; knowledge, no comprehensive review has yet addressed this specific intersection within the stated timeframe, which underscores the novelty and contribution of this study. The research methodology involved the systematic selection of peer-reviewed articles from leading academic databases, including Scopus, Web of Science and Google Scholar, thereby ensuring a rigorous and comprehensive examination of the subject matter.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e2.1. Eligibility criteria\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eA systematic study of all peer-reviewed and published research works relevant to the study of the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning was conducted for examination. Only research works published in English between 2015 and 2025 were included in the analysis. A proper criterion for inclusion was adapted to ensure the inclusion of research papers that specifically focus on this topic and exclude those that do not. Consequently, only peer-reviewed research works that fundamentally converge on the applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning, and that include a research framework or methodology specific to these aspects, were exclusively considered. The inclusion and exclusion criteria for this study are tabulated as in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024).\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eProposed Inclusion and Exclusion Criteria.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCriteria\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eInclusion\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eExclusion\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTopic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eArticle papers focusing on applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eArticle papers not focusing on applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eResearch Framework\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eThe Articles must include research framework or methodology for applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eArticles must exclude research framework or methodology for applications and impact of data visualization tools and techniques for learning and decision-making in education and machine learning\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLanguage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eArticles published in English language only\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eArticles published in languages other than English\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePeriod\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eArticles between 2015 to 2025\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eArticles outside 2015 and 2025\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e2.2. Information sources\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eA systematic search of online databases was carried out to identify relevant studies for this review. The databases Scopus, Web of Science, and Google Scholar were selected because of their broad coverage of peer-reviewed literature in the areas of data visualization, education, and machine learning. Each database was searched thoroughly using a combination of keywords related to the study topic to ensure that the most relevant articles were captured (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024). Scopus offered access to a wide range of journals and conference proceedings, while Web of Science was used to cross-check results and provide citation data to strengthen the reliability of the selected studies. Google Scholar complemented these sources by retrieving additional relevant works, including articles and dissertations that may not be indexed elsewhere. Together, the results from these three databases formed the basis of the literature review, ensuring a comprehensive and balanced collection of research works.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e2.3. Search strategy\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe literature for this research was collected from reputable online research databases, focusing on keywords that address both the technological and contextual aspects of data visualization in education and machine learning. The inclusion of terms such as \u0026ldquo;learning analytics,\u0026rdquo; \u0026ldquo;decision-making,\u0026rdquo; and \u0026ldquo;explainable AI\u0026rdquo; ensured the capture of studies relevant to diverse educational and machine learning environments. A thorough search was carried out in three main repositories: Google Scholar, Scopus, and Web of Science. To find the most relevant studies, a specific set of keywords was used. These keywords were: (\"Data Visualization\" AND (\"Education\" OR \"Learning\") AND (\"Decision-Making\" OR \"Learning Analytics\" OR \"Dashboard\") AND (\"Machine Learning\" OR \"Explainable AI\" OR \"XAI\")). This combination of terms was chosen to ensure that the search captured studies directly related to the research topic. The search focused on papers published between 2015 and 2025. This time frame was selected to provide a recent and relevant overview of the subject. The search results included 101,000 papers from Google Scholar, 585 papers from Scopus, and 101 paper from Web of Science. After collecting these papers, they were carefully reviewed and filtered to select only those that were most relevant to the research questions. This process helped to narrow down the literature to the most useful and high-quality sources for this study. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the list of online repositories that were utilized as well as the total number of results achieved before the initial screening. The Bibliometric Analysis of Study Search Keywords is illustrated in Fig.\u0026nbsp;1 (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024).\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eResults Achieved from Literature Search.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo.\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOnline Repository\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNumber of results\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eGoogle Scholar\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e101,000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWeb of Science\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e101\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eScopus\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e585\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e101,686\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e2.4. Selection process\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eFour researchers (JM, TPM, HM) independently reviewed the titles and abstracts of the first 123 records retrieved from the search. Any differences in the selections were discussed collectively until an agreement was reached. After this initial screening, the researchers worked in pairs to independently review the titles and abstracts of all retrieved articles. In cases where differences of opinion arose, discussions were held to determine which articles should proceed to full-text evaluation. If the researchers could not reach an agreement, the third researcher was consulted to make the final decision. Afterwards, three researchers (JM, TPM, HM) independently assessed the full-text articles to determine whether they met the inclusion criteria. As before, any disagreements were resolved through discussion. If needed, the fourth researcher (BAT) was involved in making the final call on whether to include or exclude the articles, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e2\u003c/span\u003e (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024).\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e2.5. Data collection process\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eTo ensure that the data collected from the studies was accurate, a structured approach was followed to minimize errors and reduce bias. Three reviewers independently extracted data from each study under the supervision of a fourth reviewer. Any discrepancies in the extracted data were discussed until a consensus was reached. A standardized data extraction form, adapted from previous systematic reviews, was used to maintain consistency across all reviewers. No automation tools were applied in the extraction process. All data were carefully entered and double-checked for accuracy to avoid errors. When information in the studies was unclear, a thorough review of all available materials was conducted, including supplementary information, appendices, and related publications, to clarify the data. In cases where concerns remained, the fourth reviewer, who is a subject matter expert, was consulted to ensure the reliability of the interpretation. For studies with multiple reports, clear criteria were established to select the most relevant version, prioritizing the most recent and comprehensive publications within the period 2015 to 2025. Where discrepancies were identified across reports, the methods and outcomes were compared in detail to resolve differences. Only studies written in English were included, while articles published in other languages were excluded to maintain consistency in the analysis and to avoid misinterpretation due to language differences, as illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024).\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e2.6. Data items\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThis section provides a comprehensive overview of the data items sought in this systematic review, focusing on both primary outcomes and additional variables relevant to the impact of data visualization tools and techniques on learning and decision-making in education and machine learning. The primary outcomes encompass dimensions such as improvements in learning outcomes, decision-making effectiveness, usability, user engagement, and model interpretability. In addition to these outcomes, the review also considers study and participant characteristics, intervention details, technological factors, and contextual influences, ensuring a thorough understanding of the application and effects of visualization approaches in educational and machine learning environments. This approach allows for a nuanced analysis of how data visualization contributes to enhanced learning experiences and more informed decision-making across diverse settings and conditions.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec15\" class=\"Section3\"\u003e\u003ch2\u003e2.6.1 Data Collection Method\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eEfforts were made to ensure a comprehensive understanding of the impact of data visualization tools and techniques on learning and decision-making in education and machine learning. Relevant outcomes were thoroughly identified and defined to capture the educational, cognitive, and technological dimensions influenced by these visualization approaches. Our approach was designed to synthesize robust evidence that reflects the transformative effects of visualization in supporting learning processes and informed decision-making. The primary outcomes of this systematic review centered on several key domains directly related to the application of data visualization in education and machine learning contexts. Learning Outcomes were a major focus, defined by measurable improvements in academic performance, knowledge retention, and student engagement. We sought all results that reflected how visualization tools supported comprehension, reduced learning difficulties, and facilitated self-regulated learning. These learning-related measures provided clear insights into the practical benefits of visualization in enhancing educational processes.Decision-Making Effectiveness was another critical outcome, assessed by examining the accuracy, speed, and quality of decisions informed by visualization tools. This included both educational decisions (such as early identification of at-risk learners or curriculum adjustments) and machine learning decisions (such as model evaluation, debugging, or interpretability). All relevant metrics that demonstrated improvements in decision-making were considered to capture a comprehensive view of visualization\u0026rsquo;s impact. Usability and User Experience were also evaluated by reviewing studies that reported on system usability, ease of interpretation, user satisfaction, and workload reduction. We specifically sought results that demonstrated how visualization tools enabled intuitive interactions, reduced cognitive load, and encouraged continued use. These measures provided valuable evidence of the human-centered effectiveness of visualization. Finally, Model Interpretability and Transparency was emphasized, particularly in machine learning contexts where explainable AI (XAI) techniques were visualized. Outcomes in this domain included user trust, understanding of model behaviour, and the ability to identify model limitations or biases. Studies reporting improvements in model interpretability through visualization were included to evaluate their role in supporting transparent and ethical decision-making.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section3\"\u003e\u003ch2\u003e2.6.2 Definition of Collected Data Variables\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn addition to the primary outcomes, several additional variables were collected to provide a deeper understanding of the context in which data visualization tools and techniques were applied. These variables were essential for interpreting the results and understanding the broader implications of visualization use in education and machine learning environments. Study characteristics were recorded, including the educational level (K-12, higher education, professional learning), subject domain, and institutional context, to assess how widely applicable the findings were across different learning settings. These details helped to situate the outcomes and highlight the diversity of approaches among the studies included. Participant characteristics were also captured, focusing on information about the users of the visualization tools such as students, instructors, administrators, or data scientists as well as their level of digital literacy and prior experience with visualization systems. This information was crucial for understanding the human factors influencing how effectively visualization tools supported learning and decision-making. Intervention characteristics were described in detail, including the type of visualization tools used (e.g., dashboards, heatmaps, learning analytics interfaces, model explanation plots), the data sources they relied on (LMS logs, assessments, clickstream data, or machine learning models), and whether the tools provided real-time or static feedback. These characteristics were key for evaluating the technological depth, usability, and integration of the interventions within the learning or ML pipeline.\u003c/p\u003e\u003cp\u003eOther important considerations included technological and contextual factors, such as whether the visualizations were interactive, adaptive, or personalized, and how they aligned with pedagogical goals or model validation workflows. These factors allowed us to better understand not just whether visualization was used, but how it shaped user behavior and decision outcomes. Finally, external influences such as institutional policies, ethical considerations, and data privacy constraints were noted, as these can strongly affect the adoption and success of visualization approaches in education and ML contexts. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, our approach included a careful manual search across Google Scholar, Scopus, and Web of Science to ensure that the most relevant studies were captured. These searches were carefully refined to retrieve accurate and focused information, ensuring that our analysis was specific to the applications and impacts of data visualization in learning and decision-making. By clearly defining these outcomes and contextual variables, this systematic review delivers a robust and comprehensive analysis of the role of visualization tools and techniques in supporting educational and machine learning practices. This methodical approach strengthens the reliability and practical relevance of the findings, making them valuable for researchers, practitioners, and decision-makers seeking to leverage visualization for better outcomes.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eData Variables Collected.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"2\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eField\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDescription\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eStudy characteristics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eEducational level, subject area, and institutional context to understand the setting of each study.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eParticipant characteristics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRoles of users (students, teachers, administrators) and their level of engagement with the visualization tools.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIntervention characteristics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDetails of visualization tools and techniques used (dashboards, heatmaps, model explanation plots), their data sources, integration with platforms (e.g., LMS, ML pipelines), and scope of application.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTechnological factors\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWhether the visualization provided real-time or static feedback, personalization or interactivity features, and alignment with learning or decision-support goals.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExternal influences\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eInstitutional policies, data privacy requirements, ethical considerations, and other contextual factors affecting the adoption or success of visualization tools.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e2.7. Study risk of bias assessment\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn the studies included in this review, particularly those investigating the impact of data visualization tools and techniques on learning outcomes and decision-making, it was essential to critically evaluate the risk of bias to ensure the validity and reliability of the findings. To achieve this, we applied appropriate quality assessment tools for non-randomized and experimental studies. For observational and quasi-experimental studies, the Newcastle-Ottawa Scale (NOS) was used, evaluating each study across three domains: Selection, Comparability, and Outcome. For randomized controlled trials and experimental designs, the Cochrane Risk of Bias Tool (RoB 2) was employed to assess randomization process, deviations from intended interventions, missing data, outcome measurement, and selective reporting. Each study was rated systematically, with a maximum of one star awarded per item within the Selection and Outcome categories and up to two stars for Comparability in the NOS assessment, reflecting the overall quality of the study. RoB 2 assessments were summarized as \u0026ldquo;low risk,\u0026rdquo; \u0026ldquo;some concerns,\u0026rdquo; or \u0026ldquo;high risk.\u0026rdquo; As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003e, the risk of bias assessment was conducted by four independent reviewers (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024). Each study was assessed individually to ensure objectivity, and disagreements between reviewers were resolved through discussion. Where consensus could not be reached, a fourth reviewer was consulted to make the final decision. For studies with unclear or missing methodological information particularly those involving proprietary visualization tools, learning analytics dashboards, or machine learning explainability techniques additional verification steps were undertaken. This included cross-referencing study details across reputable sources such as Scopus, Web of Science, and Google Scholar to clarify uncertainties. A comprehensive manual search was also conducted to ensure no relevant information was overlooked. No automation tools were used during this process, ensuring a careful and thorough evaluation of bias for each included study.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003e2.8. Synthesis methods\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe flow chart below in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e illustrates the systematic approach used in our review of data visualization tools and techniques for learning and decision-making in education and machine learning (Mtjilibe et al., 2024; Khamis, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Borrego-Ruiz \u0026amp; Borrego, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thango \u0026amp; Obokoh, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Guo et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Tanchangya et al., 2025; Nethanani et al., 2024; Pachiou et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Silva Le\u0026oacute;n et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ngcobo et al., 2024). Starting with the Study Selection Process, we identified and screened studies based on the eligibility criteria established earlier. Next, Data Standardization involved cleaning and organizing the extracted data to ensure consistency across all included studies. In the Data Analysis phase, the results were summarized and presented in tables and graphs, and initial comparisons were performed to highlight trends in learning outcomes, decision-making improvements, usability, and model interpretability. The flow then moves to Heterogeneity Assessment, where we evaluated variability between studies through subgroup analysis, comparing factors such as visualization type, educational level, and decision-making context. Finally, Bias Assessment was carried out to identify potential biases and ensure transparency in our review process. This structured approach ensures that the findings of this review are comprehensive, reliable, and reproducible.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn this systematic review on the application and impact of data visualization tools and techniques for learning and decision-making in education and machine learning, we employed rigorous synthesis methods to ensure that our results were robust, transparent, and reproducible. To determine the eligibility of studies for synthesis, we meticulously tabulated the characteristics of each study and compared them against our predefined synthesis groups. This approach allowed us to include only the most relevant studies, ensuring that our findings were both valid and closely aligned with the objectives of the review. In preparing the data for synthesis, we addressed any missing information by reviewing supplementary materials and, where necessary, standardizing outcome measures to maintain consistency across studies. The results were presented using structured tables and visual summaries, such as bar charts and comparative graphs, which provided a clear representation of key outcomes and helped to identify trends, patterns, and outliers effectively. The synthesis of results was conducted using a narrative and, where appropriate, quantitative approach, with subgroup analyses focusing on factors such as type of visualization (e.g., dashboards, heatmaps, model explanation plots), educational level, and decision-making context. This approach provided nuanced insights into how these variables influenced learning outcomes, usability, and decision-making effectiveness. Heterogeneity was further explored through subgroup comparisons to identify potential sources of variation, such as interactivity level or real-time feedback features. Sensitivity analyses were also carried out to assess the robustness of the findings, ensuring that the conclusions drawn were supported by consistent and reliable evidence. Through this comprehensive and systematic approach, we were able to provide a meaningful aggregation of the evidence, offering valuable insights for educators, researchers, and decision-makers seeking to leverage visualization tools and techniques to enhance learning outcomes and support informed decision-making in education and machine learning environments.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec19\" class=\"Section3\"\u003e\u003ch2\u003e2.8.1. Eligibility for Synthesis\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eTo determine study eligibility for inclusion in our systematic review on data visualization tools and techniques for learning and decision-making in education and machine learning, each study was carefully evaluated for its relevance and alignment with the review\u0026rsquo;s objectives. We manually assessed and compared each study\u0026rsquo;s characteristics such as the type of visualization tool, data source, educational or machine learning context, and reported outcomes\u0026mdash;against our predefined synthesis groups. A matrix was created to visually compare the scope and methodologies of the studies with our inclusion criteria, ensuring a thorough and objective evaluation. This process ensured that only studies directly relevant to the role of data visualization in supporting learning and decision-making were included, thereby improving the overall rigor, reliability, and focus of the review.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section3\"\u003e\u003ch2\u003e2.8.2. Data Preparation for Synthesis\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn this review, data preparation involved converting and standardizing information extracted from the included studies on data visualization tools and techniques to ensure consistency before synthesis. For example, when visualization outcomes or effectiveness measures were reported differently across studies, mathematical adjustments were applied to convert these into a uniform scale, enabling comparability. In addition, handling missing data was a crucial aspect of the analysis. When key indicators, such as effectiveness percentages, visualization performance metrics, or decision-making outcomes, were not fully reported, we employed established methods such as data triangulation and, where appropriate, statistical imputation to estimate missing values. This process ensured that the dataset remained comprehensive and reliable, thereby enhancing the robustness of the analysis and allowing for more accurate synthesis of findings across educational and machine learning contexts.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section3\"\u003e\u003ch2\u003e2.8.3. Tabulation and Visual Display of Results\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eResults from individual studies and synthesis efforts were organized using both tabular and graphical methods to enhance clarity and facilitate cross-comparison. Tabular structures were employed to present the data in a structured format, where outcomes were categorized by domains such as visualization tools, visualization techniques, learning contexts, and decision-making impacts. Within each domain, studies were ordered according to their methodological rigor and assessed risk of bias, ensuring that the most reliable evidence was highlighted. In addition to tabular presentation, graphical methods were used to visually summarize findings across studies. Comparative charts and Sankey diagrams were employed to map the relationships between visualization tools, techniques, and educational or machine learning applications. Network diagrams were also used to depict co-occurrence of visualization methods with decision-making outcomes. These visual displays allowed trends to be revealed over time and across different contexts, facilitating the identification of gaps, dominant approaches, and underrepresented methods within the literature.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec22\" class=\"Section3\"\u003e\u003ch2\u003e2.8.4. Synthesis of Results\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eDuring our manual search across online repositories such as Google Scholar, Scopus, and Web of Science, we systematically reviewed and synthesized the results of relevant studies on data visualization tools and techniques. The synthesis process was guided by the type of data reported and the variability observed across studies. To account for methodological and contextual differences, we evaluated the applicability of both descriptive and comparative synthesis approaches, depending on the level of heterogeneity among study outcomes. The choice of synthesis method was informed by the characteristics of the data and our assumptions about consistency in reported impacts across different educational and machine learning contexts. After exporting the extracted data into Excel, we created comparative charts and visual mappings (e.g., Sankey diagrams, heatmaps, and trend analyses) to inspect the distribution of visualization tools, techniques, and outcomes. This initial visual inspection enabled us to identify recurring patterns, gaps, and areas of divergence across studies, offering a more nuanced understanding of how visualization contributes to learning enhancement and decision-making effectiveness.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec23\" class=\"Section3\"\u003e\u003ch2\u003e2.8.5. Exploring Causes of Heterogeneity\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eSubgroup analyses were conducted to explore potential sources of heterogeneity, such as differences in study settings, visualization tools employed and reported outcome measures. Specific analyses focused on factors like the educational context (e.g., higher education, K\u0026ndash;12, online learning), the type of visualization tool or technique used (e.g., dashboards, heatmaps, storytelling, interactive graphs), and the application domain (education versus machine learning). We also examined cognitive load considerations, user types (e.g., students, analysts, educators), and geographic location to assess how these factors influenced the effectiveness of visualization in supporting learning and decision-making. These analyses helped identify underlying patterns and relationships that contributed to variability across studies, highlighting the conditions under which visualization techniques are most effective.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec24\" class=\"Section3\"\u003e\u003ch2\u003e2.8.6. Sensitivity Analyses\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eSensitivity analyses were conducted to evaluate the robustness of the synthesis results in relation to the assumptions and methodological choices made during the review. These analyses included testing the impact of excluding studies that were assessed as having a high risk of bias, as well as examining how the results changed when alternative synthesis approaches (e.g., narrative vs. quantitative comparison) were applied. We also explored the influence of studies that reported incomplete or inconsistent outcome measures, such as engagement levels, decision-making accuracy, or cognitive load, to ensure that findings were not disproportionately shaped by a small subset of studies. This process strengthened the reliability and validity of the conclusions by addressing potential sources of bias and confirming that the overall patterns observed remained consistent across different analytical scenarios.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec25\" class=\"Section2\"\u003e\u003ch2\u003e2.9. Reporting bias assessment\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn conducting our systematic review on the application of data visualization tools and techniques for learning and decision-making in education and machine learning, it was crucial to assess the risk of bias due to potentially missing results, particularly those arising from selective publication or selective reporting of outcomes. We recognized that such biases could significantly affect the validity and reliability of our synthesis, and thus, we employed a structured and rigorous approach to address this concern. Our assessment of reporting bias was carried out using a combination of established statistical and graphical methods. Specifically, contour-enhanced funnel plots were utilized as a visual tool to detect asymmetries in the data. These plots were carefully examined to determine whether missing studies were more likely due to reporting bias or chance. The inclusion of statistical significance contours enabled a clear differentiation between the two, offering a reliable visual representation of potential biases.\u003c/p\u003e\u003cp\u003eFor this assessment, we did not develop new tools but relied on widely accepted techniques extensively documented in prior systematic reviews. The methodological rigor of these tools was central to our process. Contour-enhanced funnel plots provided a straightforward yet effective way to evaluate the distribution of studies, allowing us to detect and account for reporting biases in our synthesis. The assessment was designed to minimize subjectivity, ensuring the robustness of our findings. Multiple independent reviewers were involved in this process, and any disagreements were resolved through consensus discussions or, when necessary, by consulting a methodological expert. This collaborative approach strengthened the objectivity of our interpretations. We deliberately avoided automation tools for this stage, instead using manual approaches such as creating charts and plots in Excel. This hands-on method allowed for close inspection of the data, ensuring that subtle patterns or potential biases were not overlooked.\u003c/p\u003e\u003cp\u003eTo further validate our results, comprehensive manual searches were conducted across multiple repositories, including Google Scholar, Scopus, and Web of Science. These cross-references were essential in identifying discrepancies and ensuring completeness, thereby reinforcing the reliability of our conclusions. Given the specific context of visualization studies in education and machine learning, we adapted standard bias assessment methods to better reflect the reporting practices of this field. Visualization-focused studies often differ in reporting style from other domains such as medicine or business, necessitating these contextual adaptations. By tailoring our methods to align with the nature of the studies reviewed, we ensured methodological soundness and contextual accuracy. To promote transparency and reproducibility, all approaches employed in this review are thoroughly documented and made available in the supplementary materials. This commitment to openness allows other researchers to replicate our analysis or build upon it in future work, thereby enhancing the rigor and reliability of systematic research on data visualization for learning and decision-making.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec26\" class=\"Section2\"\u003e\u003ch2\u003e2.10. Certainty assessment\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed literature was evaluated based on five quality assessment (QA) criteria to ensure rigor and relevance:\u003c/p\u003e\u003cp\u003eQA1: The clarity and explicitness of the research aim.\u003c/p\u003e\u003cp\u003eQA2: The specification and transparency of data collection methods.\u003c/p\u003e\u003cp\u003eQA3: The clear definition and explanation of the data mining and business intelligence processes.\u003c/p\u003e\u003cp\u003eQA4: The application of a well-defined and appropriate research methodology.\u003c/p\u003e\u003cp\u003eQA5: The contribution of the research findings to the enhancement of existing literature on Data Visualization Tools and Techniques for Learning and Decision-Making in Education and Machine Learning.\u003c/p\u003e\u003cp\u003eThe certainty assessment responses are rated on a scale from zero (0) to one (1). A 'No' response is assigned '0' points, a score of '0.5' is given if the criterion is 'Partially' met, and '1' point is assigned for a 'Yes' response. All five criteria are scored using this scale. Each piece of literature under review can receive a total score between 0 and 5 points. The results of the certainty assessment for the collected literature on the applications of data visualization tools and techniques in education and machine learning are presented in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCertainty Assessment Results for Collected Literature on Data Visualization Tools and Techniques for Learning and Decision-Making in Education and Machine Learning.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRef.\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eQA1\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eQA2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eQA3\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eQA4\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eQA5\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003e% grading\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Gon\u0026ccedil;alves, T., Maciel, C., \u0026amp; Rodrigues, R. 2017) ;(D\u0026rsquo;Alessio, F., Aitella, R., Giannini, M., \u0026amp; Burrai, R. 2024); (Liu, Y. (2025); (Oral, A., Chawla, N., Wijkstra, H., Mahyar, N., \u0026amp; Dimara, E. 2025).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e2.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e50\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Azevedo, R., et al. (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2017\u003c/span\u003e); Zhu, Y. 2017)\u0026nbsp;;(Wang, Y., et al. 2024); (Chakraborty, A., et al. 2024); (Kumar, R. 2024);.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e60\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Zhu, Y., et al. 2018);( Dimara, E., \u0026amp; Stasko, J. 2018).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e3.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e70\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Zhu, Y., Gon\u0026ccedil;alves, T., \u0026amp; Rodrigues, R. 2018);( Dimara, E., \u0026amp; Stasko, J. 2018); (Alhadad, S. 2018); (Paiva, R., et al. \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2018\u003c/span\u003e); (Bergram, S., \u0026amp; Ochan, J. 2018); (Huang, Y., et al. 2018); (Sosulski, K. \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2018\u003c/span\u003e);( Lacefield, R., \u0026amp; Applegate, L. 2018); (Tantalaki, N., et al. 2018); (Bergram, S., \u0026amp; Ochan, J. 2018); (Sosulski, K. \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2018\u003c/span\u003e).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Wolfert, S., Ge, L., Verdouw, C., \u0026amp; Bogaardt, M. 2017); (Strandberg, R., et al. (2017); Janssen, M., \u0026amp; Helbig, N. 2017); (Zhu, Y. 2017)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e4.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e(Perdana, A., Robb, A., \u0026amp; Rohde, F. \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e);( Bhat, P. 2017); (Buena\u0026ntilde;o-Fern\u0026aacute;ndez, D. 2017);(Dimara, E., \u0026amp; Stasko, J. 2018); (Alhadad, S. 2018);( Hoelscher, C., \u0026amp; Mortimer, M. 2018); (Bergram, S., \u0026amp; Ochan, J. (2018); (Huang, Y., Wu, M., Wang, Y., \u0026amp; Ouyang, L. (2018); (Sosulski, K. \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2018\u003c/span\u003e); (Tantalaki, N., Souravlas, S., \u0026amp; Roumeliotis, M. 2018);( Sedrakyan, G. 2019); (B\u0026ouml;rner, K., Bueckle, A., \u0026amp; Ginda, M. \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2019\u003c/span\u003e); (Sight and Life Magazine. 2019); (Levy-Fix, G., Kuperman, G., \u0026amp; Elhadad, N. 2019); (Aung, T., et al. \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2019\u003c/span\u003e); (Luo, W. \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e2019\u003c/span\u003e); (Li, X., et al. 2019); (Milligan, R. 2019); (Stanca, C., et al. \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e2019\u003c/span\u003e); (Guarese, R., et al. \u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e2020\u003c/span\u003e); (Redondo, E., et al. \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e2020\u003c/span\u003e); (Peddoju, S., \u0026amp; Upadhyay, A. 2020); (Briggs, M. 2020); (Cheng, J., et al. 2020); (Rawat, P., et al. 2021);( Kumar, S., et al. 2021); (Dy, A., et al. \u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e2021\u003c/span\u003e); (Alshareef, A., et al. \u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e2021\u003c/span\u003e); (Talukder, M., \u0026amp; Deb, K. 2021); (Cepero, M., et al. 2021); (Rodr\u0026iacute;guez-Echeverr\u0026iacute;a, S. 2021); (Fern\u0026aacute;ndez-Garc\u0026iacute;a, J. C. 2021); (Gore, C., \u0026amp; Odisho, K. 2021); (Conejero Manzano, J., et al. 2021);( Moh\u0026rsquo;d Ali, H., et al. 2021); (Zytek, A., et al. \u003cspan citationid=\"CR77\" class=\"CitationRef\"\u003e2021\u003c/span\u003e); (Yuan, Y., Liu, H., \u0026amp; Kuang, W. 2021); (Dimara, E., et al. \u003cspan citationid=\"CR79\" class=\"CitationRef\"\u003e2021\u003c/span\u003e); (Mahmud, M., et al. 2022); (Vallet, F., et al. 2022); (Sakib, S. 2022); (El Morr, C., et al. 2022); (Martins, A., et al. 2022); (Murumba, S. 2022);( Patel, R. 2022); (Zheng, Y., et al. 2022); (Ak, F. 2022);( Pera, A. \u003cspan citationid=\"CR89\" class=\"CitationRef\"\u003e2022\u003c/span\u003e); (Jenkins, J. 2022); (Kamolsin, T., \u0026amp; Phu, S. 2022); (Donohoe, P., \u0026amp; Costello, F. 2022); (Bali, S., et al. \u003cspan citationid=\"CR93\" class=\"CitationRef\"\u003e2022\u003c/span\u003e); (Martynenko, A., et al. 2022); (Kamissoko, D., et al. \u003cspan citationid=\"CR95\" class=\"CitationRef\"\u003e2022\u003c/span\u003e); (Ren, Y. 2022); (Zhang, L., et al. 2023); (Pazouki, M., et al. 2023); (Diao, H., \u0026amp; Wei, S. 2023); (Bertone, E., \u0026amp; Stewart, R. A. 2023); (Llaha, A., Aliu, D., \u0026amp; Kad\u0026euml;na, A. 2023); (Rahimi Ardabili, F., et al. 2023) ; (Ouyang, L. 2024);( Shahidan, S., et al. 2024); (Mahyar, N., \u0026amp; Dimara, E. 2024); (Shinde, A. 2024); (Hossain, M., Yasmin, F., Biswas, T., \u0026amp; Asha, S. 2024); (Uddin, M. 2024); (Shahidan, S., Ibrahim, H., \u0026amp; Jamaluddin, A. 2024); (Bach, J., et al. 2024); (Chen, L., et al. 2024); (Sotiropoulos, D., Giormezis, N., Pertsas, D., \u0026amp; Tsirkas, N. 2024);( Zheng, Y., Lillis, D., \u0026amp; Campbell, R. 2024); (Romero-Organvidez, F., Horcas, J., Galindo, J., \u0026amp; Benavides, D. (2024); (Yin, H., et al. 2024);( Mauludina, E., Mulyani, H., Winarningsih, S., \u0026amp; Susanto, A. 2024); (Geisler, M., \u0026amp; Allwood, C. (2024); Then, E., \u0026amp; Bigby, C. 2024); (Aluja, T., Balada, F., Garc\u0026iacute;a, J., \u0026amp; Garc\u0026iacute;a, P. 2024); (Kollar, J., Kika, K., \u0026amp; Mazurova, L. 2025);( Zaheer, H., Hanif, A., Sarwar, M., \u0026amp; Talib, M. 2025); (Pham, T., et al. 2025); (Grolli, R., et al. 2025).\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eTo support the conclusions of this systematic review on the applications of data visualization tools and techniques for learning and decision-making in education and machine learning, we undertook a rigorous assessment of the certainty of the evidence. The strength and reliability of our findings depend on a systematic evaluation process, which we carried out using the GRADE (Grading of Recommendations, Assessment, Development, and Evaluations) framework. GRADE is a globally recognized system that offers a comprehensive and transparent approach to assessing the quality of evidence, ensuring that the conclusions drawn are both credible and well-founded. The certainty of the evidence across key outcomes was meticulously evaluated using several critical factors. First, we closely examined the precision of reported measures by considering sample sizes and the clarity of outcome reporting across the studies. Narrow confidence intervals coupled with large or well-defined samples were indicative of a high level of certainty in the evidence, as they suggest more reliable and precise estimates of visualization impacts. We also assessed the consistency of findings by comparing results across included studies. High consistency, where studies demonstrated similar effects (e.g., on engagement, decision accuracy, or cognitive load), contributed to greater certainty. Any observed heterogeneity was thoroughly analysed to understand its sources and potential influence on the overall findings.\u003c/p\u003e\u003cp\u003eFurthermore, the potential for bias was evaluated using an adapted version of the Cochrane Risk of Bias tool. Studies with a low risk of bias were considered to contribute more significantly to the overall certainty of the evidence. We also judged directness based on the alignment of study populations, interventions, and outcomes with the research questions of this review. High directness such as studies explicitly focusing on visualization for educational or machine learning decision-making strengthened the support for our conclusions, leading to greater confidence in the evidence. Based on these factors, the certainty of evidence was categorized as follows: High certainty was assigned when studies were consistent, precise, directly applicable, and exhibited a low risk of bias. Moderate certainty was applied when there were minor concerns about one factor, such as some inconsistency or a moderate risk of bias. Low certainty was given when significant concerns existed in multiple areas, including imprecision, inconsistency, or a high risk of bias. Very low certainty was assigned when critical issues were present across all factors, significantly undermining confidence in the results. To ensure the relevance of the GRADE approach to this review, we adapted it specifically for outcomes related to visualization effectiveness, including learning enhancement, cognitive load management, and decision-making improvements in education and machine learning contexts. Multiple independent reviewers assessed the certainty of evidence for each outcome. Disagreements were resolved through consensus discussions, ensuring a balanced and thorough evaluation. Additionally, where possible, we sought supplementary data or clarification from study authors to support the certainty assessments.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec28\" class=\"Section2\"\u003e\u003ch2\u003e3.1. Study selection\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eIn this systematic review, the study selection process followed a rigorous and structured approach to ensure the inclusion of relevant and high-quality research articles. Three prominent online databases Google Scholar, Web of Science, and Scopus were systematically searched to identify studies that met the inclusion criteria. Specifically, the search retrieved 101 000 records from Google Scholar, 101 record from Web of Science, and 585 records from Scopus, resulting in a total of 101 685 initial records. Following this, duplicate entries were removed, leaving 37074 unique records. These records underwent a preliminary screening process, during which their titles and abstracts were assessed for relevance to the review\u0026rsquo;s criteria. This step resulted in the selection of 34 full-text documents for a more detailed evaluation. After a comprehensive review of these full-text documents, 123 studies were deemed eligible for inclusion in the final systematic review. The included studies consisted of 67 journal articles, 4 book chapters, 32 conference papers, and 1 dissertation.\u003c/p\u003e\u003cp\u003eThe overall study selection process is depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003e, which provides a detailed PRISMA flowchart outlining the progression of records through each stage of the review.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eAdditionally, the distribution of articles obtained from each database is illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e, highlighting the contributions of the three databases to the final pool of studies. These visualizations enhance the transparency of the selection process and facilitate the replication of this methodology by other researchers.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec29\" class=\"Section2\"\u003e\u003ch2\u003e3.2. Research Distribution by Published Works\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe temporal distribution of research outputs reveals varying intensities of scholarly focus across the observed years. As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e, publication activity demonstrates periods of steady growth interspersed with notable fluctuations. Between 2017 and 2019, there was a consistent rise in published works, followed by a visible decline in 2020. This dip may be attributed to contextual factors such as global disruptions to academic activity. A renewed surge in publications is observed from 2021 onward, culminating in a significant peak in 2024, which marks the highest volume of research outputs within the period. The decline recorded in 2025, although provisional, suggests an incomplete data capture for the year rather than a definitive reduction in scholarly output.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec30\" class=\"Section2\"\u003e\u003ch2\u003e3.3. Country Distribution of Reviewed Papers\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe geographical distribution of research contributions reveals a marked imbalance across countries. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e, a majority of publications originate from a small group of nations. The United States leads with 24.39% of the reviewed works, followed closely by China (18.70%) and India (10.57%). Other significant contributors include Brazil, France, Germany, and the UK, each contributing between 5\u0026ndash;9%. These countries collectively constitute the \u0026ldquo;high contribution\u0026rdquo; group, which accounts for approximately 85% of the total reviewed works. A \u0026ldquo;moderate contribution\u0026rdquo; cluster, ranging between 2\u0026ndash;5%, includes nations such as Malaysia, Romania, Spain, Bangladesh, and Greece. Meanwhile, the \u0026ldquo;low contribution\u0026rdquo; group (below 2%) is comprised of a wider set of countries\u0026mdash;including Ukraine, Hungary, Indonesia, Saudi Arabia, and others\u0026mdash;that collectively represent 12% of contributions.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec31\" class=\"Section2\"\u003e\u003ch2\u003e3.4. Distribution of Publications\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe analysis of publication types reveals a strong preference for traditional scholarly outlets. As presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003e, journal articles dominate with 69.92% of the reviewed works, reflecting their established role as the primary medium for disseminating peer-reviewed knowledge. Conference papers account for 26.02%, underscoring their significance as venues for presenting emerging findings, networking, and receiving timely feedback within academic and professional communities. In contrast, book Chaps.\u0026nbsp;(3.25%) and dissertations (0.81%) represent a relatively minor proportion, collectively falling within the low-contribution category (\u0026lt;\u0026thinsp;5%). Their limited presence suggests that while these forms provide specialized or exploratory insights, they remain less central to mainstream scholarly communication in this domain.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec32\" class=\"Section2\"\u003e\u003ch2\u003e3.5. Distribution of Databases Used\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eAn examination of the databases employed in the reviewed studies highlights the dominance of a few indexing platforms. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e10\u003c/span\u003e, Google Scholar was the most frequently utilized source, accounting for 52.03% of the studies. Its accessibility and wide coverage likely contribute to its prominence, especially for interdisciplinary and exploratory research. Scopus follows with 30.08%, reflecting its strong reputation for indexing peer-reviewed and high-quality academic outputs. Meanwhile, the Web of Science represents 17.89% of usage, emphasizing its role in providing rigorously curated bibliographic records. The reliance on these three databases illustrates both a preference for comprehensive accessibility and the perceived authority of established indexing services.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec33\" class=\"Section2\"\u003e\u003ch2\u003e3.6. Distribution of Visualization Tools\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed studies employed a diverse range of visualization tools, reflecting both accessibility and domain-specific preferences. As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e11\u003c/span\u003e, Tableau emerged as the most widely used tool (44.72%), highlighting its popularity for interactive dashboards and intuitive visual analytics. Power BI (14.63%) and MS Excel (8.94%) followed, indicating strong reliance on business intelligence and traditional spreadsheet-based tools. Programming-based tools such as Python (8.13%), Matplotlib (8.13%), and Seaborn (5.69%) were also frequently applied, demonstrating the growing integration of data science approaches in visualization research. Specialized platforms like VOSviewer (3.25%) catered to bibliometric and network analysis. Less frequently cited tools, including D3.js, JavaScript, scikit-learn, and Taiwan-specific platforms (each \u0026lt;\u0026thinsp;1%), suggest niche but important contributions to visualization diversity.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec34\" class=\"Section2\"\u003e\u003ch2\u003e3.7. Distribution of Visualization Techniques\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed studies applied a variety of visualization techniques, reflecting the multidimensional purposes of data-driven decision-making. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e12\u003c/span\u003e, dashboards were the most dominant (26.83%), underscoring their value in integrating diverse data sources into interactive and actionable interfaces. Traditional forms such as bar graphs (16.26%) and line graphs (12.20%) remained widely used, emphasizing their clarity and accessibility for general audiences. Advanced techniques like heatmaps (11.38%), scatter plots (8.94%), and time series graphs (5.69%) were frequently adopted for trend detection, correlation analysis, and temporal monitoring. Meanwhile, approaches such as storytelling (10.57%), bubble charts (4.88%), and trend graphs (3.25%) highlight efforts to enhance interpretability and engagement, particularly in conveying complex insights to decision-makers.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec35\" class=\"Section2\"\u003e\u003ch2\u003e3.8. Distribution of Application Domains\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed studies covered diverse domains, with the strongest emphasis on education (43.09%), reflecting the increasing role of visualization in pedagogy, learning analytics, and evidence-based curriculum design. The business domain followed closely (39.84%), where visualization is frequently applied to decision support, performance monitoring, and strategic planning. Meanwhile, policy applications (17.07%) were less prevalent but remain essential in guiding governance, sustainability, and regulatory interventions. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e13\u003c/span\u003e, these domains map onto different intensity levels: education aligns mostly with moderate usage (5\u0026ndash;25%), while business shows a stronger presence in the high category (\u0026gt;\u0026thinsp;25%), highlighting its strategic reliance on advanced visualization. Policy remains comparatively lower but steadily growing in visibility.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec36\" class=\"Section2\"\u003e\u003ch2\u003e3.9. Decision-Making Outcomes\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe outcomes of visualization-supported decision-making span multiple dimensions. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e14\u003c/span\u003e, the most common focus was on business and industry outcomes (30%), where visualization enhanced performance tracking, resource optimization, and strategic planning. This was followed by policy and governance (15%) and healthcare \u0026amp; clinical applications (15%), demonstrating growing adoption of visualization for managing public health, clinical diagnostics, and regulatory oversight. Other identified outcomes include tool evaluation and framework testing (10%), decision accuracy and quality (10%), and educational impact (10%), where visualization strengthened learning gains, interpretability, and evidence-based instruction. Collectively, these findings illustrate that visualization does not serve only technical efficiency but also broader societal and institutional goals.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec37\" class=\"Section2\"\u003e\u003ch2\u003e3.10. Outcomes on Cognitive Load\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eStudies addressing visualization and decision-making frequently focused on how design choices shape cognitive load. As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e15\u003c/span\u003e, the most prominent strategies were cognitive load reduction approaches (25%) and simplicity and clarity in design (20%), both of which highlight the importance of minimizing unnecessary complexity in visual outputs. Conversely, a notable share of studies (20%) still identified complexity and overload risks, underscoring challenges related to high-dimensional data and poorly designed interfaces. Meanwhile, user-centered adaptation (10%) and interactive or immersive solutions (10%) reflect efforts to align visualization with user needs and emerging technologies. Finally, applied or domain-specific practices (15%) suggest that effective strategies must often be tailored to the context of use, such as education, healthcare, or business decision environments.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec38\" class=\"Section2\"\u003e\u003ch2\u003e3.11. User Groups\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed studies targeted a variety of user groups, reflecting the diverse contexts in which visualization supports decision-making. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e16\u003c/span\u003e, the largest share was directed toward analysts (32.52%), who rely on visualization for technical and operational insights. Managers (19.51%) and researchers (17.07%) followed, highlighting the use of visualization both for decision-making in professional settings and for knowledge production in academia. Students (17.07%) also represented a significant group, demonstrating visualization\u0026rsquo;s role in learning, skill development, and educational engagement. Other identified groups include healthcare practitioners (7.32%), citizens (5.69%), and data scientists (0.81%), the latter reflecting a more niche but growing specialization in technical applications. These clusters map onto broader categories such as professional/technical users, decision-makers, academic learners and producers, domain-specific practitioners, and civic users, emphasizing the widespread but differentiated adoption of visualization across domains.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec39\" class=\"Section2\"\u003e\u003ch2\u003e3.12. Challenges and Limitations\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe reviewed literature identified several recurring challenges and limitations that influence the effectiveness and applicability of visualization in decision-making contexts. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig16\" class=\"InternalRef\"\u003e17\u003c/span\u003e, the most prominent concerns include complexity and scalability (20%) and cognitive and interpretability issues (18%), both of which highlight the difficulty of balancing technical sophistication with clarity and usability. Other recurring themes were data quality and integration (15%), technical and tool limitations (14%), and user training and literacy gaps (12%), which underline barriers to adoption across diverse contexts. Additionally, concerns around evaluation and evidence gaps (10%), ethical and social issues (7%), and global relevance and generalizability (4%) suggest that while visualization is a powerful tool, its reliability and inclusivity remain constrained. Together, these findings reveal the importance of methodological rigor, equitable design, and training support to ensure visualization reaches its full potential.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Proposed Framework for Visualization in Decision-Making","content":"\u003cdiv id=\"Sec41\" class=\"Section2\"\u003e\u003ch2\u003e4.1. Inputs: Knowledge Sources and Research Channels\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe framework begins with scholarly inputs, which were shaped by the dominant role of journal articles and conference papers (Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003e) and retrieved primarily from Google Scholar, Scopus, and Web of Science (Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e10\u003c/span\u003e). These sources form the knowledge base that drives methodological diversity and ensures academic rigor.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec42\" class=\"Section2\"\u003e\u003ch2\u003e4.2. Contextual Dimensions: Geographic and Domain Distributions\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eResearch is geographically concentrated in a few countries (USA, China, India, Brazil, France, UK, Germany), reflecting knowledge asymmetry (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). Domains of application\u0026mdash;education, business, and policy (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e13\u003c/span\u003e)\u0026mdash;shape the way visualization tools are applied, with education focusing on engagement, business on strategy, and policy on governance.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec43\" class=\"Section2\"\u003e\u003ch2\u003e4.3. Methods: Tools and Techniques\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eVisualization practices draw from a wide spectrum of tools\u0026mdash;ranging from Tableau, Power BI, and Excel to Python and Matplotlib (Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e11\u003c/span\u003e)\u0026mdash;and techniques such as dashboards, bar graphs, line charts, and storytelling (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e12\u003c/span\u003e). Together, these form the operational core of visualization-supported decision-making, balancing traditional clarity with interactive innovation.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec44\" class=\"Section2\"\u003e\u003ch2\u003e4.4. Mechanisms: Cognitive and Decision Processes\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe cognitive layer addresses how visualization influences decision-making through:\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eCognitive load management\u003c/b\u003e (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e15\u003c/span\u003e), via strategies such as simplification, clarity, and adaptive design.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eDecision-making outcomes\u003c/b\u003e (Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e14\u003c/span\u003e), spanning improved business performance, educational impact, healthcare, and governance.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThis layer represents the mechanism of translation: how raw data, once visualized, becomes actionable insight.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec45\" class=\"Section2\"\u003e\u003ch2\u003e4.5. Users: Target Groups and Roles\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eDifferent user groups shape adoption and interpretation (Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e16\u003c/span\u003e). Analysts, managers, and researchers dominate, but learners (students) and practitioners (healthcare, citizens) emphasize inclusivity. The framework thus highlights tailored visualization strategies based on user literacy, technical capacity, and decision context.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec46\" class=\"Section2\"\u003e\u003ch2\u003e4.6. Boundaries: Challenges and Limitations\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eFinally, the framework is bounded by structural challenges (Fig.\u0026nbsp;\u003cspan refid=\"Fig16\" class=\"InternalRef\"\u003e17\u003c/span\u003e):\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eComplexity and scalability issues\u003c/b\u003e (20%),\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eCognitive/interpretability barriers\u003c/b\u003e (18%),\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eData quality/integration constraints\u003c/b\u003e (15%), and\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eUser literacy gaps\u003c/b\u003e (12%).\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThese challenges define the limits of transferability and point toward areas requiring future innovation.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"5. Discussion","content":"\u003cdiv id=\"Sec48\" class=\"Section2\"\u003e\u003ch2\u003e5.1. How has research on data visualization and learning analytics evolved over time?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe temporal distribution of reviewed works shows clear fluctuations in scholarly activity. Between 2017 and 2019, there was a steady rise in publications, followed by a noticeable dip in 2020, likely reflecting disruptions in academic research activity. From 2021 onward, the field regained momentum, culminating in a remarkable peak in 2024 \u0026mdash; the highest year of publication output (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e). The decline observed in 2025 is likely provisional, reflecting incomplete data capture rather than a genuine reduction. These patterns suggest that DV and LA research has grown in relevance over time, particularly in response to increasing demands for evidence-driven decision-making.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec49\" class=\"Section2\"\u003e\u003ch2\u003e5.2. Which countries and regions contribute most to this research field?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe geographical distribution demonstrates a pronounced imbalance (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). The United States (24.39%), China (18.70%), and India (10.57%) dominate, together accounting for over half of the publications. Other notable contributors include Brazil, France, Germany, and the UK (5\u0026ndash;9% each), forming a high-contribution cluster of around 85% of total output. By contrast, moderate contributors such as Malaysia, Romania, and Spain (2\u0026ndash;5%), and a large set of low contributors (\u0026lt;\u0026thinsp;2%), underscore the global unevenness of research capacity. This suggests the need for more inclusive, cross-regional collaboration to ensure broader perspectives in visualization and learning analytics research.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec50\" class=\"Section2\"\u003e\u003ch2\u003e5.3. What publication outlets are most common?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eJournal articles remain the dominant outlet, representing 69.92% of the reviewed works (Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003e). This reflects the centrality of peer-reviewed journals in shaping scholarly discourse. Conference papers, at 26.02%, play a vital complementary role, especially for emerging ideas and community engagement. Book Chaps.\u0026nbsp;(3.25%) and dissertations (0.81%) are comparatively underrepresented, indicating that specialized or exploratory contributions remain less mainstream. This publication distribution emphasizes the prioritization of rigor and peer-review while still allowing space for exploratory dissemination.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec51\" class=\"Section2\"\u003e\u003ch2\u003e5.4. Which databases are most frequently used in this research?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eGoogle Scholar is the most widely used source, accounting for 52.03% of studies, followed by Scopus (30.08%) and Web of Science (17.89%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e10\u003c/span\u003e). The reliance on Google Scholar highlights its accessibility and inclusiveness but also raises questions about selectivity and quality control. Scopus and Web of Science provide stronger filtering and indexing standards, yet their lower shares suggest barriers in access or coverage. This distribution underscores a trade-off between comprehensiveness and methodological rigor in database selection.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec52\" class=\"Section2\"\u003e\u003ch2\u003e5.5. What visualization tools and techniques are most applied?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eTableau emerges as the leading tool (44.72%), followed by Power BI (14.63%) and MS Excel (8.94%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e11\u003c/span\u003e). This highlights the dominance of user-friendly, business-intelligence\u0026ndash;oriented platforms. Programming-based tools like Python (8.13%), Matplotlib (8.13%), and Seaborn (5.69%) represent growing but still secondary approaches. Less frequently applied tools (e.g., VOSviewer, D3.js) remain niche. On techniques, dashboards dominate (26.83%), reflecting their value in integrating data into actionable formats (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e12\u003c/span\u003e). Traditional methods such as bar graphs (16.26%) and line graphs (12.20%) remain foundational, while advanced approaches like heatmaps (11.38%), scatter plots (8.94%), and storytelling (10.57%) indicate attempts to balance analytical depth with user engagement. Collectively, these findings reveal both continuity with conventional methods and increasing diversification into interactive and immersive techniques.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec53\" class=\"Section2\"\u003e\u003ch2\u003e5.6. In which domains is DV and LA most applied?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe largest share of studies focus on education (43.09%), underscoring the importance of visualization for pedagogy, learning analytics, and institutional decision-making (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e13\u003c/span\u003e). Business (39.84%) closely follows, highlighting its strategic reliance on visualization for operational and managerial decision-making. Policy (17.07%) applications remain less developed but are gaining visibility, particularly in governance and sustainability contexts. These distributions reflect both the dominance of established application areas and the potential for growth in underexplored domains.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec54\" class=\"Section2\"\u003e\u003ch2\u003e5.7. What outcomes are associated with visualization-supported decision-making?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eDecision-making outcomes are diverse (Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e14\u003c/span\u003e). The most common are business and industry outcomes (30%), where visualization supports performance tracking and resource optimization. Policy and governance outcomes (15%) and healthcare/clinical applications (15%) reveal growing institutional and societal uptake. Educational outcomes (10%), decision accuracy and quality (10%), and tool/framework evaluations (10%) further emphasize the broad impact of visualization. These findings suggest that DV and LA are not limited to efficiency gains but contribute meaningfully to learning, governance, and healthcare.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec55\" class=\"Section2\"\u003e\u003ch2\u003e5.8. How does visualization affect cognitive load in decision-making?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe literature identifies both benefits and risks (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e15\u003c/span\u003e). Strategies to reduce cognitive load (25%) and emphasize simplicity and clarity in design (20%) are prominent, highlighting their role in facilitating user comprehension. However, complexity and overload risks remain significant (20%), often arising from poorly designed or high-dimensional visuals. User-centered adaptation (10%), interactive/immersive solutions (10%), and domain-specific practices (15%) show promising strategies to tailor visualization effectively. Together, these results suggest that while visualization can mitigate cognitive burden, careful design choices are critical to avoid unintended overload.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec56\" class=\"Section2\"\u003e\u003ch2\u003e5.9. Who are the primary user groups?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe distribution of user groups reveals that analysts (32.52%) dominate, reflecting the technical and operational nature of much of this research (Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e16\u003c/span\u003e). Managers (19.51%) and researchers (17.07%) represent additional large groups, highlighting both decision-making and academic knowledge production. Students (17.07%) reflect the educational emphasis of the field, while healthcare practitioners (7.32%), citizens (5.69%), and data scientists (0.81%) represent smaller but important communities. These findings suggest that visualization research is heavily skewed toward professional and technical users but has meaningful extensions into education and public engagement.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec57\" class=\"Section2\"\u003e\u003ch2\u003e5.10. What challenges and limitations persist?\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eAs summarized in Fig.\u0026nbsp;\u003cspan refid=\"Fig16\" class=\"InternalRef\"\u003e17\u003c/span\u003e, challenges include complexity and scalability (20%), cognitive and interpretability issues (18%), data quality and integration (15%), and tool/technical limitations (14%). User training and literacy gaps (12%) further restrict uptake. Additionally, evaluation and evidence gaps (10%), ethical and social concerns (7%), and issues of global relevance (4%) highlight persistent barriers. These challenges emphasize the need for methodological rigor, equitable design, and capacity building to ensure the sustainable adoption of DV and LA across diverse contexts.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"6. Conclusion","content":"\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThis review synthesized 123 studies (2015\u0026ndash;2025) to evaluate the applications and impact of data visualization (DV) and learning analytics (LA) in supporting educational decision-making. To structure the evidence, a taxonomy was developed encompassing visualization tools, visualization techniques, application domains, decision-making outcomes, cognitive load considerations, user groups, and reported challenges. Findings reveal a steady growth in research outputs with notable peaks between 2021\u0026ndash;2024 (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e), though contributions remain geographically concentrated in the USA, China, and India (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). Journal articles dominated publication outlets (Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003e), and Google Scholar, Scopus, and Web of Science were the most common sources (Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e10\u003c/span\u003e). Tool distribution was led by Tableau, Power BI, and Excel (Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e11\u003c/span\u003e), while dashboards, bar graphs, and line graphs emerged as the most frequently applied techniques (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e12\u003c/span\u003e). Education and business were the leading application domains (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e13\u003c/span\u003e), with decision-making outcomes most prominent in business/industry, policy, and healthcare (Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e14\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eCognitive load outcomes highlighted both the benefits of simplicity and risks of overload (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e15\u003c/span\u003e), underscoring trade-offs between clarity and complexity. User groups were led by analysts, managers, and researchers/students, while healthcare practitioners and citizens were comparatively underrepresented (Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e16\u003c/span\u003e). Persistent challenges included complexity and scalability (20%), interpretability (18%), data integration (15%), and training gaps (12%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig16\" class=\"InternalRef\"\u003e17\u003c/span\u003e). These results emphasize three critical insights. First, methodological transparency and standardized reporting remain limited, particularly regarding tool selection and visualization design. Second, reliance on descriptive dashboards reflects underutilization of advanced methods such as predictive modeling and network analysis, restricting the field\u0026rsquo;s capacity to fully support evidence-based education. Third, user diversity and contextual variation are often overlooked, with limited attention to K\u0026ndash;12, resource-constrained, or non-Western environments.To address these gaps, future research should pursue (i) rigorous methodological frameworks and longitudinal validation studies, (ii) hybrid visualization models integrating advanced analytics with user-centered design, and (iii) comparative analyses across regions and institutional contexts to promote inclusivity and scalability. A conceptual framework (Fig.\u0026nbsp;18) is proposed to integrate inputs, context, methods, mechanisms, users, and boundaries, offering a structured pathway for advancing DV and LA adoption in education.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eBuena\u0026ntilde;o-Fern\u0026aacute;ndez, D. (2019). The use of tools of data mining to decision making in engineering education\u0026mdash;A systematic mapping study. \u003cem\u003eComputer Applications in Engineering Education, 27\u003c/em\u003e(6), 1633\u0026ndash;1651. https://doi.org/10.1002/cae.22100\u003c/li\u003e\n \u003cli\u003eZhu, Z. (2017). Interactive data visualization techniques applied to healthcare decision making. In Computer Science \u0026amp; IT (pp. 1\u0026ndash;15). IGI Global. https://doi.org/10.4018/978-1-5225-1994-7.ch001\u003c/li\u003e\n \u003cli\u003eAnderson, J. S., \u0026amp; Williams, S. K. (2019). Turning data into better decision making: Asking questions, collecting and analyzing data in a personal analytics project. \u003cem\u003eDecision Sciences Journal of Innovative Education, 17\u003c/em\u003e(2), 126\u0026ndash;145. https://doi.org/10.1111/dsji.12173\u003c/li\u003e\n \u003cli\u003eChatti, M. A., Dyckhoff, A. L., Schroeder, U., \u0026amp; Th\u0026uuml;s, H. (2012). A reference model for learning analytics. \u003cem\u003eInternational Journal of Technology Enhanced Learning, 4\u003c/em\u003e(5/6), 318\u0026ndash;331. https://doi.org/10.1504/IJTEL.2012.051816\u003c/li\u003e\n \u003cli\u003eFerguson, R. (2012). Learning analytics: Drivers, developments and challenges. \u003cem\u003eInternational Journal of Technology Enhanced Learning, 4\u003c/em\u003e(5/6), 304\u0026ndash;317. https://doi.org/10.1504/IJTEL.2012.051816\u003c/li\u003e\n \u003cli\u003ePerdana, A., Robb, A., \u0026amp; Wijkstra, M. (2021). From information to choice: A critical inquiry into visualization tools for decision making. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics, 30\u003c/em\u003e(1), 359\u0026ndash;369. https://doi.org/10.1109/TVCG.2023.3282426\u003c/li\u003e\n \u003cli\u003eJanssen, M., Charalabidis, Y., \u0026amp; Zuiderwijk, A. (2012). Benefits, adoption barriers and myths of open data and open government. \u003cem\u003eGovernment Information Quarterly, 29\u003c/em\u003e(4), 258\u0026ndash;268. https://doi.org/10.1016/j.giq.2015.11.009\u003c/li\u003e\n \u003cli\u003eDimara, E., \u0026amp; Stasko, J. (2022). A critical reflection on visualization research: Where do decision-making tasks hide? \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics, 28\u003c/em\u003e(1), 1128\u0026ndash;1138. https://doi.org/10.1109/TVCG.2021.3114813\u003c/li\u003e\n \u003cli\u003eDimara, E., \u0026amp; Stasko, J. (2022). \u003cem\u003eFrom information to choice: A critical inquiry into visualization tools for decision making\u003c/em\u003e [Data and materials]. OSF. https://osf.io/nrasz/\u003c/li\u003e\n \u003cli\u003eHuang, M. L., \u0026amp; Nguyen, Q. V. (2012). A survey of visualization for decision making: Data and knowledge visualization. \u003cem\u003eInternational Journal of Information Technology \u0026amp; Decision Making, 11\u003c/em\u003e(1), 165\u0026ndash;188. https://doi.org/10.1142/S0219622012400040\u003c/li\u003e\n \u003cli\u003eAlhadad, S. S. J. (2018). Visualizing data to support judgement, inference, and decision making in learning analytics: Insights from cognitive psychology and visualization science. \u003cem\u003eJournal of Learning Analytics, 5\u003c/em\u003e(2), 60\u0026ndash;85. https://doi.org/10.18608/jla.2018.52.5\u003c/li\u003e\n \u003cli\u003ePaiva, R. C. F., \u0026amp; Filho, J. A. (2019). Teachers\u0026rsquo; perceptions on traditional and non-traditional data visualization for pedagogical decision-making. In \u003cem\u003eProceedings of the Brazilian Symposium on Computers in Education (SBIE)\u003c/em\u003e (pp. 1577\u0026ndash;1586). SBC. https://doi.org/10.5753/cbie.sbie.2019.1577\u003c/li\u003e\n \u003cli\u003eKrist, C. (2017). \u003cem\u003eData visualization made simple: Insights into becoming visual\u003c/em\u003e. New York, NY: Routledge.\u003c/li\u003e\n \u003cli\u003eSedig, K., \u0026amp; Parsons, P. (2019). Design of visualizations for human-information interaction: A pattern-based framework. \u003cem\u003eInformation Visualization, 18\u003c/em\u003e(1), 1\u0026ndash;32. https://doi.org/10.1080/10496505.2019.1638264\u003c/li\u003e\n \u003cli\u003eKhan, A., \u0026amp; Tariq, R. (2018). Big-data-driven safety decision-making: A conceptual framework and its influencing factors. \u003cem\u003eSafety Science, 110\u003c/em\u003e, 411\u0026ndash;423. https://doi.org/10.1016/j.ssci.2018.09.014\u003c/li\u003e\n \u003cli\u003eWolfert, S., Ge, L., Verdouw, C., \u0026amp; Bogaardt, M. J. (2017). Big data in smart farming\u0026ndash;a review. \u003cem\u003eAgricultural systems\u003c/em\u003e, \u003cem\u003e153\u003c/em\u003e, 69-80. https://www.sciencedirect.com/science/article/pii/S0308521X16303754\u003c/li\u003e\n \u003cli\u003eGon\u0026ccedil;alves, A. F. D., Maciel, A. M. A., \u0026amp; Rodrigues, R. L. (2017). Development of a data mining education framework for data visualization in distance learning environments. In \u003cem\u003eInternational conference on software engineering and knowledge engineering\u003c/em\u003e. https://ksiresearch.org/seke/seke17paper/seke17paper_130.pdf\u003c/li\u003e\n \u003cli\u003eAzevedo, R., Millar, G. C., Taub, M., Mudrick, N. V., Bradbury, A. E., \u0026amp; Price, M. J. (2017, March). Using data visualizations to foster emotion regulation during self-regulated learning with advanced learning technologies: a conceptual framework. In \u003cem\u003eProceedings of the seventh international learning analytics \u0026amp; knowledge conference\u003c/em\u003e (pp. 444-448). https://dl.acm.org/doi/abs/10.1145/3027385.3027440\u003c/li\u003e\n \u003cli\u003eWilliamson, W. (2022). Learning analytics dashboards in higher education: A systematic review. \u003cem\u003eComputers \u0026amp; Education, 180\u003c/em\u003e, 104413. https://doi.org/10.1016/j.compedu.2022.104413.\u003c/li\u003e\n \u003cli\u003eMtjilibe, Tshepang and Rameetse, Emmanuel and Mgwenya, Nkosinathi and Thango, Bonginkosi, Exploring the Challenges and Opportunities of Social Media for Organizational Engagement in SMEs: A Comprehensive Systematic Review (July 06, 2024). Available at SSRN: https://ssrn.com/abstract=4998542 or http://dx.doi.org/10.2139/ssrn.4998542.\u003c/li\u003e\n \u003cli\u003eKhamis, A. Smart Mobility Education and Capacity Building for Sustainable Development: A Review and Case Study. Sustainability 2025, 17(17), 7999; https://doi.org/10.3390/su17177999.\u003c/li\u003e\n \u003cli\u003eBorrego-Ruiz, A.; Borrego, J. Microbial Metabolomes in Alzheimer\u0026rsquo;s Disease: From Pathogenesis to Therapeutic Potential. Curr. Issues Mol. Biol. 2025, 47(9), 724; https://doi.org/10.3390/cimb47090724.\u003c/li\u003e\n \u003cli\u003eThango, B. A., \u0026amp; Obokoh, L. (2024). Techno-Economic Analysis of Hybrid Renewable Energy Systems for Power Interruptions: A Systematic Review. Eng, 5(3), 2108-2156. https://doi.org/10.3390/eng5030112.\u003c/li\u003e\n \u003cli\u003eGuo, C.; Xu, S.; Guo, X. Metabolic Engineering of Terpenoid Biosynthesis in Medicinal Plants: From Genomic Insights to Biotechnological Applications. Curr. Issues Mol. Biol. 2025, 47(9), 723; https://doi.org/10.3390/cimb47090723.\u003c/li\u003e\n \u003cli\u003eTanchangya, T.; Sarker, T.; Rahman, J.; Islam, M.; Islam, N.; Siddiqi, K. Mapping Blockchain Applications in FinTech: A Systematic Review of Eleven Key Domains. Information 2025, 16(9), 769; https://doi.org/10.3390/info16090769.\u003c/li\u003e\n \u003cli\u003eNethanani, Ronewa and matlombe, luzuko and Vuko, Siphethuxolo N. and Thango, Bonginkosi, Customer Relationship Management (CRM) Systems and their Impact on SMEs Performance: A Systematic Review (October 21, 2024). Available at SSRN: https://ssrn.com/abstract=4996185 or http://dx.doi.org/10.2139/ssrn.4996185.\u003c/li\u003e\n \u003cli\u003ePachiou, A.; Zervou, E.; Sykaras, N.; Tortopidis, D.; Ioannidis, A.; Jung, R.; Strauss, F.; Kourtis, S. Patient-Reported Outcomes of Digital Versus Conventional Impressions for Implant-Supported Fixed Dental Prostheses: A Systematic Review and Meta-Analysis. J. Pers. Med. 2025, 15(9), 427; https://doi.org/10.3390/jpm15090427.\u003c/li\u003e\n \u003cli\u003eSilva Le\u0026oacute;n, P.; Cruz Salinas, L.; Farf\u0026aacute;n Chilicaus, G.; Castro Ijiri, G.; Chuquitucto Cotrina, L.; Heredia Llatas, F.; Ramos Farro\u0026ntilde;\u0026aacute;n, E.; P\u0026eacute;rez N\u0026aacute;jera, C. Digital Technologies for Young Entrepreneurs in Latin America: A Systematic Review of Educational Innovations (2018\u0026ndash;2024). Soc. Sci. 2025, 14(9), 537; https://doi.org/10.3390/socsci14090537.\u003c/li\u003e\n \u003cli\u003eNgcobo, Kwanele and Bhengu, Sandiswa and Mudau, Ambani and Thango, Bonginkosi and Lerato, Matshaka, Enterprise Data Management: Types, Sources, and Real-Time Applications to Enhance Business Performance - A Systematic Review (September 26, 2024). Systematic Review | September 2024 | DOI: 10.20944/preprints202409.1913.v1, Available at SSRN: https://ssrn.com/abstract=4968451 or http://dx.doi.org/10.2139/ssrn.4968451.\u003c/li\u003e\n \u003cli\u003eStrandberg, P. E., Afzal, W., \u0026amp; Sundmark, D. (2018, October). Decision making and visualizations based on test results. In \u003cem\u003eProceedings of the 12th ACM/IEEE international symposium on empirical software engineering and measurement\u003c/em\u003e (pp. 1-10). https://dl.acm.org/doi/abs/10.1145/3239235.3268921\u003c/li\u003e\n \u003cli\u003eBhat, A. S. (2017). Data visualization of requests for information to support construction decision-making (Doctoral dissertation, University of British Columbia). https://open.library.ubc.ca/soa/cIRcle/collections/ubctheses/24/items/1.0344010\u003c/li\u003e\n \u003cli\u003eBuena\u0026ntilde;o‐Fernandez, D., Villegas‐CH, W., \u0026amp; Luj\u0026aacute;n‐Mora, S. (2019). The use of tools of data mining to decision making in engineering education\u0026mdash;A systematic mapping study. \u003cem\u003eComputer applications in engineering education\u003c/em\u003e, \u003cem\u003e27\u003c/em\u003e(3), 744-758. https://onlinelibrary.wiley.com/doi/abs/10.1002/cae.22100\u003c/li\u003e\n \u003cli\u003eZhu, Z., Hoon, H. B., \u0026amp; Teow, K. L. (2017). Interactive data visualization techniques applied to healthcare decision making. In \u003cem\u003eDecision Management: Concepts, Methodologies, Tools, and Applications\u003c/em\u003e (pp. 1157-1171). IGI Global Scientific Publishing. https://www.igi-global.com/chapter/interactive-data-visualization-techniques-applied-to-healthcare-decision-making/176799\u003c/li\u003e\n \u003cli\u003eJanssen, M., \u0026amp; Helbig, N. (2018). Innovating and changing the policy-cycle: Policy-makers be prepared!. \u003cem\u003eGovernment Information Quarterly\u003c/em\u003e, \u003cem\u003e35\u003c/em\u003e(4), S99-S105. https://www.sciencedirect.com/science/article/abs/pii/S0740624X15300265\u003c/li\u003e\n \u003cli\u003eOral, E., Chawla, R., Wijkstra, M., Mahyar, N., \u0026amp; Dimara, E. (2023). From information to choice: A critical inquiry into visualization tools for decision making. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e30\u003c/em\u003e(1), 359-369. https://ieeexplore.ieee.org/abstract/document/10292614\u003c/li\u003e\n \u003cli\u003eAk, M. F. (2020, April). A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications. In \u003cem\u003eHealthcare\u003c/em\u003e (Vol. 8, No. 2, p. 111). MDPI. https://www.mdpi.com/2227-9032/8/2/111\u003c/li\u003e\n \u003cli\u003eDimara, E., \u0026amp; Stasko, J. (2021). A critical reflection on visualization research: Where do decision making tasks hide?. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(1), 1128-1138. https://ieeexplore.ieee.org/abstract/document/9552846\u003c/li\u003e\n \u003cli\u003eRaineri, P., \u0026amp; Molinari, F. (2021). Innovation in data visualisation for public policy making. In \u003cem\u003eThe data shake: opportunities and obstacles for urban policy making\u003c/em\u003e (pp. 47-59). Cham: Springer International Publishing. https://library.oapen.org/bitstream/handle/20.500.12657/47327/9783030636937.pdf?sequence=1#page=59\u003c/li\u003e\n \u003cli\u003eAlhadad, S. S. (2018). Visualizing data to support judgement, inference, and decision making in learning analytics: Insights from cognitive psychology and visualization science. \u003cem\u003eJournal of Learning Analytics\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e(2), 60-85. https://learning-analytics.info/index.php/JLA/article/view/5815\u003c/li\u003e\n \u003cli\u003eHoelscher, J., \u0026amp; Mortimer, A. (2018). Using Tableau to visualize data and drive decision-making. \u003cem\u003eJournal of Accounting Education\u003c/em\u003e, \u003cem\u003e44\u003c/em\u003e, 49-59. https://www.sciencedirect.com/science/article/abs/pii/S0748575117301951\u003c/li\u003e\n \u003cli\u003ePaiva, R., Bittencourt, I. I., Lemos, W., Vinicius, A., \u0026amp; Dermeval, D. (2018, June). Visualizing learning analytics and educational data mining outputs. In \u003cem\u003eInternational Conference on Artificial Intelligence in Education\u003c/em\u003e (pp. 251-256). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-319-93846-2_46\u003c/li\u003e\n \u003cli\u003eBergram, K., \u0026amp; Ochan, B. (2018). Data-driven Biased Decision-making?-Exploring the landscape between dashboards, visualization literacy and decision bias. https://lup.lub.lu.se/student-papers/search/publication/8950609\u003c/li\u003e\n \u003cli\u003eHuang, L., Wu, C., Wang, B., \u0026amp; Ouyang, Q. (2018). Big-data-driven safety decision-making: a conceptual framework and its influencing factors. \u003cem\u003eSafety science\u003c/em\u003e, \u003cem\u003e109\u003c/em\u003e, 46-56. https://www.sciencedirect.com/science/article/abs/pii/S0925753518300973\u003c/li\u003e\n \u003cli\u003eSosulski, K. (2018). Data visualization made simple: insights into becoming visual. Routledge. https://www.taylorfrancis.com/books/mono/10.4324/9781315146096/data-visualization-made-simple-kristen-sosulski\u003c/li\u003e\n \u003cli\u003eLacefield, W. E., \u0026amp; Applegate, E. B. (2018). Data Visualization in Public Education: Longitudinal Student-, Intervention-, School-, and District-Level Performance Modeling. \u003cem\u003eOnline Submission\u003c/em\u003e. https://eric.ed.gov/?id=ED582891\u003c/li\u003e\n \u003cli\u003eTantalaki, N., Souravlas, S., \u0026amp; Roumeliotis, M. (2019). Data-driven decision making in precision agriculture: The rise of big data in agricultural systems. \u003cem\u003eJournal of agricultural \u0026amp; food information\u003c/em\u003e, \u003cem\u003e20\u003c/em\u003e(4), 344-380. https://www.tandfonline.com/doi/abs/10.1080/10496505.2019.1638264\u003c/li\u003e\n \u003cli\u003eAl-Kassab, J., Ouertani, Z. M., Schiuma, G., \u0026amp; Neely, A. (2014). Information visualization to support management decisions. \u003cem\u003eInternational Journal of Information Technology \u0026amp; Decision Making\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(02), 407-428. https://www.worldscientific.com/doi/abs/10.1142/S0219622014500497\u003c/li\u003e\n \u003cli\u003eManorat, R., Becker, L., \u0026amp; Flory, A. (2019). Global data visualization tools to empower decision-making in nutrition. \u003cem\u003eSight and Life\u003c/em\u003e, \u003cem\u003e33\u003c/em\u003e(1), 108-114. https://datadent.org/wp-content/uploads/2022/08/SightandLifeMagazine_2019_Data_in_Nutrition_GlobalDataVisualizationTools.pdf\u003c/li\u003e\n \u003cli\u003eSedrakyan, G., Mannens, E., \u0026amp; Verbert, K. (2019). Guiding the choice of learning dashboard visualizations: Linking dashboard design and data visualization concepts. \u003cem\u003eJournal of Computer Languages\u003c/em\u003e, \u003cem\u003e50\u003c/em\u003e, 19-38. https://www.sciencedirect.com/science/article/abs/pii/S1045926X18301009\u003c/li\u003e\n \u003cli\u003ePerdana, A., Robb, A., \u0026amp; Rohde, F. (2019). Interactive data and information visualization: unpacking its characteristics and influencing aspects on decision-making. \u003cem\u003ePacific Asia Journal of the Association for Information Systems\u003c/em\u003e, \u003cem\u003e11\u003c/em\u003e(4), 4. https://aisel.aisnet.org/pajais/vol11/iss4/4/\u003c/li\u003e\n \u003cli\u003eB\u0026ouml;rner, K., Bueckle, A., \u0026amp; Ginda, M. (2019). Data visualization literacy: Definitions, conceptual frameworks, exercises, and assessments. \u003cem\u003eProceedings of the National Academy of Sciences\u003c/em\u003e, \u003cem\u003e116\u003c/em\u003e(6), 1857-1864. https://www.pnas.org/doi/abs/10.1073/pnas.1807180116\u003c/li\u003e\n \u003cli\u003eLevy-Fix, G., Kuperman, G. J., \u0026amp; Elhadad, N. (2019). Machine learning and visualization in clinical decision support: current state and future directions. \u003cem\u003earXiv preprint arXiv:1906.02664\u003c/em\u003e. https://arxiv.org/abs/1906.02664\u003c/li\u003e\n \u003cli\u003eAung, T., Niyeha, D., Shagihilu, S., Mpembeni, R., Kaganda, J., Sheffel, A., \u0026amp; Heidkamp, R. (2019). Optimizing data visualization for reproductive, maternal, newborn, child health, and nutrition (RMNCH\u0026amp;N) policymaking: data visualization preferences and interpretation capacity among decision-makers in Tanzania. \u003cem\u003eGlobal health research and policy\u003c/em\u003e, \u003cem\u003e4\u003c/em\u003e(1), 4. https://link.springer.com/article/10.1186/s41256-019-0095-1\u003c/li\u003e\n \u003cli\u003eLuo, W. (2019). User choice of interactive data visualization format: The effects of cognitive style and spatial ability. \u003cem\u003eDecision Support Systems\u003c/em\u003e, \u003cem\u003e122\u003c/em\u003e, 113061. https://www.sciencedirect.com/science/article/abs/pii/S0167923619300776\u003c/li\u003e\n \u003cli\u003eVerma, K., Bhardwaj, S., Arya, R., Islam, M. S. U., Bhushan, M., Kumar, A., \u0026amp; Samant, P. (2019). Latest tools for data mining and machine learning. \u003cem\u003eInternational Journal of Innovative Technology and Exploring Engineering\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e(9), 18-23. https://www.researchgate.net/profile/Megha-Bhushan/publication/335455343_Latest_Tools_for_Data_Mining_and_Machine_Learning/links/6762adbf7784cf161e0964a3/Latest-Tools-for-Data-Mining-and-Machine-Learning.pdf\u003c/li\u003e\n \u003cli\u003eLi, Q., Wang, P., Sun, Y., Zhang, Y., \u0026amp; Chen, C. (2019). Data-driven decision making in graduate students\u0026rsquo; research topic selection: Cognitive processes and challenging factors. \u003cem\u003eAslib journal of information management\u003c/em\u003e, \u003cem\u003e71\u003c/em\u003e(5), 657-676. https://www.emerald.com/ajim/article-abstract/71/5/657/38009/Data-driven-decision-making-in-graduate-students?redirectedFrom=fulltext\u003c/li\u003e\n \u003cli\u003eQu, Z., Zhou, Y., Nguyen, Q. V., \u0026amp; Catchpoole, D. R. (2019, January). Using visualization to illustrate machine learning models for genomic data. In \u003cem\u003eProceedings of the Australasian computer science week multiconference\u003c/em\u003e (pp. 1-8). https://dl.acm.org/doi/abs/10.1145/3290688.3290719\u003c/li\u003e\n \u003cli\u003eMilligan, J. N. (2019). Learning Tableau 2019: Tools for Business Intelligence, data prep, and visual analytics. Packt Publishing Ltd.https://books.google.co.za/books?hl=en\u0026amp;lr=\u0026amp;id=-jmPDwAAQBAJ\u0026amp;oi=fnd\u0026amp;pg=PP1\u0026amp;dq=Learning+Tableau+2019:+Tools+for+Business+Intelligence,+Data+Prep,+and+\u003cbr\u003eAnalysis\u0026amp;ots=MlsRYyEpwf\u0026amp;sig=tOwwi8vyRDxIXF29br7k8ERQGiw\u0026amp;redir_esc=y#v=onepage\u0026amp;q=Learning%20Tableau%202019%3A%20Tools%20for%20\u003cbr\u003eBusiness%20Intelligence%2C%20Data%20Prep%2C%20and%20Analysis\u0026amp;f=false\u003c/li\u003e\n \u003cli\u003eStanca, L., Felea, C., Stanca, R., \u0026amp; Pintea, M. (2019, June). The impact of visualization tools on the learning engagement of accounting students. In \u003cem\u003eInternational Conference in Methodologies and intelligent Systems for Techhnology Enhanced Learning\u003c/em\u003e (pp. 148-156). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-030-23884-1_19\u003c/li\u003e\n \u003cli\u003eGuarese, R., Becker, J., Fensterseifer, H., Walter, M., Freitas, C., Nedel, L., \u0026amp; Maciel, A. (2020, September). Augmented situated visualization for spatial and context-aware decision-making. In \u003cem\u003eProceedings of the 2020 International Conference on Advanced Visual Interfaces\u003c/em\u003e (pp. 1-5). https://dl.acm.org/doi/abs/10.1145/3399715.3399838\u003c/li\u003e\n \u003cli\u003eByrd, V. L., \u0026amp; Asunda, P. A. (2020, October). Using evidence based practices and learning to enhance critical thinking skills in students through data visualization. In \u003cem\u003e2020 IEEE Frontiers in Education Conference (FIE)\u003c/em\u003e (pp. 1-9). IEEE. https://ieeexplore.ieee.org/abstract/document/9274157\u003c/li\u003e\n \u003cli\u003eRedondo, R., Herrero, \u0026Aacute;., Corchado, E., \u0026amp; Sedano, J. (2020). A decision-making tool based on exploratory visualization for the automotive industry. \u003cem\u003eApplied Sciences\u003c/em\u003e, \u003cem\u003e10\u003c/em\u003e(12), 4355. https://www.mdpi.com/2076-3417/10/12/4355\u003c/li\u003e\n \u003cli\u003ePeddoju, S. K., \u0026amp; Upadhyay, H. (2020). Evaluation of IoT data visualization tools and techniques. In \u003cem\u003eData visualization: Trends and challenges toward multidisciplinary perception\u003c/em\u003e (pp. 115-139). Singapore: Springer Singapore. https://link.springer.com/chapter/10.1007/978-981-15-2282-6_7\u003c/li\u003e\n \u003cli\u003eD\u0026apos;Souza, D. E., Bement, D., \u0026amp; Cory, K. (2022). Cross‐functional integration skills: Are business schools delivering what organizations need?. \u003cem\u003eDecision Sciences Journal of Innovative Education\u003c/em\u003e, \u003cem\u003e20\u003c/em\u003e(3), 117-130. https://onlinelibrary.wiley.com/doi/full/10.1111/dsji.12262\u003c/li\u003e\n \u003cli\u003eBriggs, T. (2020). Using Data Visualization and Dashboards to Support the Decision Making of Public Library Branch Managers. Wilmington University (Delaware). https://www.proquest.com/openview/1cd402e520032b8a6abe26c2fc10b687/1?pq-origsite=gscholar\u0026amp;cbl=51922\u0026amp;diss=y\u003c/li\u003e\n \u003cli\u003eCheng, J. C., Chen, W., Chen, K., \u0026amp; Wang, Q. (2020). Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms. \u003cem\u003eAutomation in Construction\u003c/em\u003e, \u003cem\u003e112\u003c/em\u003e, 103087. https://www.sciencedirect.com/science/article/abs/pii/S0926580518308562\u003c/li\u003e\n \u003cli\u003eRawat, S., Rawat, A., Kumar, D., \u0026amp; Sabitha, A. S. (2021). Application of machine learning and data visualization techniques for decision support in the insurance sector. \u003cem\u003eInternational Journal of Information Management Data Insights\u003c/em\u003e, \u003cem\u003e1\u003c/em\u003e(2), 100012. https://www.sciencedirect.com/science/article/pii/S2667096821000057\u003c/li\u003e\n \u003cli\u003eDimara, E., \u0026amp; Stasko, J. (2021). A critical reflection on visualization research: Where do decision making tasks hide?. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(1), 1128-1138. https://ieeexplore.ieee.org/abstract/document/9552846\u003c/li\u003e\n \u003cli\u003eDy, B., Ibrahim, N., Poorthuis, A., \u0026amp; Joyce, S. (2021). Improving visualization design for effective multi-objective decision making. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(10), 3405-3416. https://ieeexplore.ieee.org/abstract/document/9374716\u003c/li\u003e\n \u003cli\u003eAlshareef, H. N., Majrashi, A., Helal, M., \u0026amp; Tahir, M. (2021). Knowledge extraction and data visualization: a proposed framework for secure decision making using data mining. \u003cbr/\u003e\u003cem\u003eInternational Journal of Advanced Computer Science and Applications\u003c/em\u003e, \u003cem\u003e12\u003c/em\u003e(8). https://www.researchgate.net/profile/Muhammad-Tahir-63/publication/354334760_Knowledge_Extraction_and_Data_Visualization_A_Proposed_Framework_for_Secure_\u003cbr/\u003eDecision_Making_using_Data_Mining/links/63911644484e65005beec9cc/Knowledge-Extraction-and-Data-Visualization-A-Proposed-Framework-for-Secure-Decision-Making-using-Data-Mining.pdf\u003c/li\u003e\n \u003cli\u003eTalukder, A. K. A., \u0026amp; Deb, K. (2020). PaletteViz: A visualization method for functional understanding of high-dimensional Pareto-optimal data-sets to aid multi-criteria decision making. \u003cem\u003eIEEE Computational Intelligence Magazine\u003c/em\u003e, \u003cem\u003e15\u003c/em\u003e(2), 36-48. https://ieeexplore.ieee.org/abstract/document/9064747\u003c/li\u003e\n \u003cli\u003eCepero, T., Montan\u0026eacute;-Jim\u0026eacute;nez, L. G., \u0026amp; Toledo-Toledo, G. (2021). Visualization Technologies to Support Decision-Making in City Management. \u003cem\u003eProgramming and Computer Software\u003c/em\u003e, \u003cem\u003e47\u003c/em\u003e(8), 803-816. https://link.springer.com/article/10.1134/S0361768821080107\u003c/li\u003e\n \u003cli\u003eStreeb, D., El-Assady, M., Keim, D. A., \u0026amp; Chen, M. (2021). Why visualize? Arguments for visual support in decision making. \u003cem\u003eIEEE Computer Graphics and Applications\u003c/em\u003e, \u003cem\u003e41\u003c/em\u003e(2), 17-22. https://ieeexplore.ieee.org/abstract/document/9380860\u003c/li\u003e\n \u003cli\u003eShee, K., Pal, S. K., Wells, J. C., Ruiz-Morales, J. M., Russell, K., Dudani, S., ... \u0026amp; Odisho, A. Y. (2021). Interactive data visualization tool for patient-centered decision making in kidney cancer. \u003cem\u003eJCO Clinical Cancer Informatics\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e, 912-920. https://ascopubs.org/doi/full/10.1200/CCI.21.00050\u003c/li\u003e\n \u003cli\u003eConejero, J. M., Preciado, J. C., Fern\u0026aacute;ndez-Garc\u0026iacute;a, A. J., Prieto, A. E., \u0026amp; Rodr\u0026iacute;guez-Echeverr\u0026iacute;a, R. (2021). Towards the use of Data Engineering, Advanced Visualization techniques and Association Rules to support knowledge discovery for public policies. \u003cem\u003eExpert Systems with Applications\u003c/em\u003e, \u003cem\u003e170\u003c/em\u003e, 114509. https://www.sciencedirect.com/science/article/abs/pii/S0957417420311532\u003c/li\u003e\n \u003cli\u003eMoh\u0026apos;d Ali, M. A., Basahr, A., Rabbani, M. R., \u0026amp; Abdulla, Y. (2020, November). Transforming business decision making with internet of things (IoT) and machine learning (ML). In \u003cem\u003e2020 International conference on decision aid sciences and application (DASA)\u003c/em\u003e (pp. 674-679). IEEE. https://ieeexplore.ieee.org/abstract/document/9317174\u003c/li\u003e\n \u003cli\u003eZytek, A., Liu, D., Vaithianathan, R., \u0026amp; Veeramachaneni, K. (2021). Sibyl: Understanding and addressing the usability challenges of machine learning in high-stakes decision making. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(1), 1161-1171. https://ieeexplore.ieee.org/abstract/document/9552849\u003c/li\u003e\n \u003cli\u003eYuan, Y. H., Liu, C. H., \u0026amp; Kuang, S. S. (2021). An innovative and interactive teaching model for cultivating talent\u0026rsquo;s digital literacy in decision making, sustainability, and computational thinking. \u003cem\u003eSustainability\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(9), 5117. https://www.mdpi.com/2071-1050/13/9/5117\u003c/li\u003e\n \u003cli\u003eDimara, E., Zhang, H., Tory, M., \u0026amp; Franconeri, S. (2021). The unmet data visualization needs of decision makers within organizations. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e28\u003c/em\u003e(12), 4101-4112. https://ieeexplore.ieee.org/abstract/document/9408391\u003c/li\u003e\n \u003cli\u003eCui, Y., Song, X., Hu, Q., Li, Y., Shanthini, A., \u0026amp; Vadivel, T. (2021). Big data visualization using multimodal feedback in education. \u003cem\u003eComputers \u0026amp; Electrical Engineering\u003c/em\u003e, \u003cem\u003e96\u003c/em\u003e, 107544. https://www.sciencedirect.com/science/article/abs/pii/S0045790621004894\u003c/li\u003e\n \u003cli\u003eVallet, F., Khouadjia, M., Amrani, A., \u0026amp; Pouzet, J. (2021). Designing a data visualisation and analysis tool for supporting decision-making with public transportation network. \u003cem\u003eProceedings of the Design Society\u003c/em\u003e, \u003cem\u003e1\u003c/em\u003e, 1093-1102. https://www.cambridge.org/core/journals/proceedings-of-the-design-society/article/designing-a-data-visualisation-and-analysis-tool-for-supporting-decisionmaking-with-public-transportation-network/A5EB2D2288FC7F3DA7610B4A9CB1E945\u003c/li\u003e\n \u003cli\u003eSakib, S. N. (2022). Data Visualization in Data Science. https://www.cambridge.org/engage/coe/article-details/626bc5baef2ade3a51419ce1\u003c/li\u003e\n \u003cli\u003eEl-Morr, C., Jammal, M., Ali-Hassan, H., \u0026amp; El-Hallak, W. (2022). Machine Learning for Practical Decision Making. \u003cem\u003eInternational Series in Operations Research and Management Science\u003c/em\u003e. https://link.springer.com/content/pdf/10.1007/978-3-031-16990-8.pdf\u003c/li\u003e\n \u003cli\u003eMarques, B., Santos, B. S., Ara\u0026uacute;jo, T., Martins, N. C., Alves, J. B., \u0026amp; Dias, P. (2019, July). Situated visualization in the decision process through augmented reality. In \u003cem\u003e2019 23rd international conference information visualisation (IV)\u003c/em\u003e (pp. 13-18). IEEE. https://ieeexplore.ieee.org/abstract/document/8811981\u003c/li\u003e\n \u003cli\u003eMurumba, J. (2022). Learning analytics and educational data visualization in the digital era. \u003cem\u003eJournal of Innovations in Data Science and Big Data Management\u003c/em\u003e, \u003cem\u003e1\u003c/em\u003e(03), 2022. https://www.researchgate.net/profile/Julius-Murumba/publication/359093879_Learning_Analytics_and_Educational_Data_Visualization_in_the_Digital_Era/links/625869dda279ec5dd7f699a8/Learning-Analytics-and-Educational-Data-Visualization-in-the-Digital-Era.pdf\u003c/li\u003e\n \u003cli\u003eEberhard, K. (2023). The effects of visualization on judgment and decision-making: a systematic literature review. \u003cem\u003eManagement Review Quarterly\u003c/em\u003e, \u003cem\u003e73\u003c/em\u003e(1), 167-214. https://link.springer.com/article/10.1007/s11301-021-00235-8\u003c/li\u003e\n \u003cli\u003eZheng, M., Pan, X., Bermeo, N. V., Thomas, R. J., Coyle, D., O\u0026rsquo;hare, G. M., \u0026amp; Campbell, A. G. (2022). Stare: Augmented reality data visualization for explainable decision support in smart environments. \u003cem\u003eIEEE Access\u003c/em\u003e, \u003cem\u003e10\u003c/em\u003e, 29543-29557. https://ieeexplore.ieee.org/abstract/document/9727109\u003c/li\u003e\n \u003cli\u003eAk, M. F. (2020, April). A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications. In \u003cem\u003eHealthcare\u003c/em\u003e (Vol. 8, No. 2, p. 111). MDPI. https://www.mdpi.com/2227-9032/8/2/111\u003c/li\u003e\n \u003cli\u003ePera, A. (2022). The moral decision-making capacity of autonomous mobility technologies: Route planning algorithms, simulation modeling tools, and intelligent traffic monitoring systems. \u003cem\u003eContemporary Readings in Law and Social Justice\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(2), 136-153. https://www.ceeol.com/search/article-detail?id=1085225\u003c/li\u003e\n \u003cli\u003eJenkins, T. (2022). Immersive virtual shopping experiences in the retail metaverse: Consumer-driven E-commerce, blockchain-based digital assets, and data visualization tools. \u003cem\u003eLinguistic and Philosophical Investigations\u003c/em\u003e, (21), 154-169. https://www.ceeol.com/search/article-detail?id=1045820\u003c/li\u003e\n \u003cli\u003eFraz\u0026atilde;o, D. A. G., da Costa, T. S. A., de Ara\u0026uacute;jo, T. D. O., Meiguins, B. S., \u0026amp; dos Santos, C. G. R. (2021, July). A brief review of dashboard visualizations employed to support management or business decisions. In \u003cem\u003e2021 25th International Conference Information Visualisation (IV)\u003c/em\u003e (pp. 100-107). IEEE. https://ieeexplore.ieee.org/abstract/document/9582679\u003c/li\u003e\n \u003cli\u003eDonohoe, D., \u0026amp; Costello, E. (2020). Data visualisation literacy in higher education: An exploratory study of understanding of a learning dashboard tool. \u003cem\u003eInternational Journal of Emerging Technologies in Learning (iJET)\u003c/em\u003e, \u003cem\u003e15\u003c/em\u003e(17), 115-126. https://www.learntechlib.org/d/218005/\u003c/li\u003e\n \u003cli\u003eBali, S., Gunasekaran, A., Aggarwal, S., Tyagi, B., \u0026amp; Bali, V. (2022). A strategic decision-making framework for sustainable reverse operations. \u003cem\u003eJournal of Cleaner Production\u003c/em\u003e, \u003cem\u003e381\u003c/em\u003e, 135058. https://www.sciencedirect.com/science/article/abs/pii/S0959652622046327\u003c/li\u003e\n \u003cli\u003eMartynenko, A. A., Tevyashev, A. D., Kulishova, N. Y., \u0026amp; Moroz, B. I. (2022). The problem of automatic classification of pictures using an intelligent decision-making system based on the knowledge graph and fine-grained image analysis. https://ela.kpi.ua/items/6fa67074-ad49-4d45-bf91-9a45ecb9d17b\u003c/li\u003e\n \u003cli\u003eKamissoko, D., Gourc, D., Marmier, F., \u0026amp; Clement, A. (2022). A Go/No-Go Decision-Making Model Based on Risk and Multi-Criteria Techniques for Project Selection. \u003cem\u003eInternational Journal of Decision Support System Technology (IJDSST)\u003c/em\u003e, \u003cem\u003e15\u003c/em\u003e(2), 1-21. https://www.igi-global.com/article/a-gono-go-decision-making-model-based-on-risk-and-multi-criteria-techniques-for-project-selection/315641\u003c/li\u003e\n \u003cli\u003eRen, Y., Song, J., Wang, L., Lu, W., \u0026amp; Wang, X. (2022). Research on Lane-Changing Decision-Making Behavior of Intelligent Network-Connected Autonomous Vehicles (No. 2022-01-7066). SAE Technical Paper. https://www.sae.org/publications/technical-papers/content/2022-01-7066/\u003c/li\u003e\n \u003cli\u003eZhang, X., Zhou, D., Zhou, G., Cao, W., Wang, M., Wang, C., \u0026amp; Li, H. (2022, December). Research on auxiliary decision-making of power grid fault recovery based on generative adversarial imitation learning. In \u003cem\u003eProceedings of the 2022 4th International Conference on Robotics, Intelligent Control and Artificial Intelligence\u003c/em\u003e (pp. 1140-1145). https://dl.acm.org/doi/abs/10.1145/3584376.3584578\u003c/li\u003e\n \u003cli\u003ePazouki, P., Teshnizi, E. S., Bertone, E., Helfer, F., \u0026amp; Stewart, R. A. (2022). Multi-criteria decision making for a holistic assessment of sustainable alternatives in SWRO desalination: A case study. \u003cem\u003eDesalination\u003c/em\u003e, \u003cem\u003e544\u003c/em\u003e, 116127. https://www.sciencedirect.com/science/article/abs/pii/S0011916422005823\u003c/li\u003e\n \u003cli\u003eDiao, F., \u0026amp; Wei, G. (2022). EDAS method for multiple attribute group decision making under spherical fuzzy environment. \u003cem\u003eInternational Journal of Knowledge-based and Intelligent Engineering Systems\u003c/em\u003e, \u003cem\u003e26\u003c/em\u003e(3), 175-188. https://journals.sagepub.com/doi/abs/10.3233/KES-220018\u003c/li\u003e\n \u003cli\u003eAli, L., Asadi, M., Ga\u0026scaron;ević, D., Jovanović, J., \u0026amp; Hatala, M. (2013). Factors influencing beliefs for adoption of a learning analytics tool: An empirical study. \u003cem\u003eComputers \u0026amp; Education\u003c/em\u003e, \u003cem\u003e62\u003c/em\u003e, 130-148. https://www.sciencedirect.com/science/article/abs/pii/S0360131512002515\u003c/li\u003e\n \u003cli\u003eLlaha, O., Aliu, A., \u0026amp; Kadena, E. (2023). Application of clustering methods and data visualization for decision making in higher education. \u003cem\u003eJournal of Awareness\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e(3), 297-303. https://www.ceeol.com/search/article-detail?id=1205063\u003c/li\u003e\n \u003cli\u003eArdabili, B. R., Yao, S., Pazho, A. D., Bourque, L., \u0026amp; Tabkhi, H. (2023). Enhancing situational awareness in surveillance: Leveraging data visualization techniques for machine learning-based video analytics outcomes. \u003cem\u003earXiv preprint arXiv:2312.05629\u003c/em\u003e. https://arxiv.org/abs/2312.05629\u003c/li\u003e\n \u003cli\u003eKharakhash, О. (2023). Data visualization: transforming complex data into actionable insights. \u003cem\u003eAutomation of technological and business processes\u003c/em\u003e, \u003cem\u003e15\u003c/em\u003e(2), 4-12. https://journals.ontu.edu.ua/index.php/atbp/article/view/2520\u003c/li\u003e\n \u003cli\u003ePrem, E. (2023). From ethical AI frameworks to tools: a review of approaches. \u003cem\u003eAI and Ethics\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(3), 699-716. https://link.springer.com/article/10.1007/s43681-023-00258-9\u003c/li\u003e\n \u003cli\u003eYalim, C., \u0026amp; Handley, H. A. (2023). The effectiveness of visualization techniques for supporting decision-making. https://digitalcommons.odu.edu/msvcapstone/2023/datascience/1/\u003c/li\u003e\n \u003cli\u003ePala, S. K. (2017). Advance Analytics for Reporting and Creating Dashboards with Tools like SSIS, Visual Analytics and Tableau. \u003cem\u003eInternational Journal of Open Publication and Exploration\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e(2), 3006-2853.\u003cbr/\u003e https://www.researchgate.net/profile/Sravan-Pala/publication/378679002_Advance_Analytics_for_\u003cbr/\u003eReporting_and_Creating_Dashboards_with_Tools_like_SSIS_Visual_Analytics_and_Tableau/links/65e366bfc3b52a117006c436/Advance-Analytics-for-Reporting-and-Creating-Dashboards-with-Tools-like-SSIS-Visual-Analytics-and-Tableau.pdf\u003c/li\u003e\n \u003cli\u003eStanca, L., Felea, C., Stanca, R., \u0026amp; Pintea, M. (2020, June). The impact of personality, attitude and visual decision-making dashboard tools on the learning engagement of economist students. In \u003cem\u003eInternational Conference in Methodologies and intelligent Systems for Techhnology Enhanced Learning\u003c/em\u003e (pp. 106-116). Cham: Springer International Publishing. https://link.springer.com/chapter/10.1007/978-3-030-52538-5_12\u003c/li\u003e\n \u003cli\u003eNasir, F., Ahmed, A. A., Kiraz, M. S., Yevseyeva, I., \u0026amp; Saif, M. (2024). Data-Driven Decision-Making for Bank Target Marketing Using Supervised Learning Classifiers on Imbalanced Big Data. \u003cem\u003eComputers, Materials \u0026amp; Continua\u003c/em\u003e, \u003cem\u003e81\u003c/em\u003e(1). https://openurl.ebsco.com/EPDB%3Agcd%3A2%3A1405570/detailv2?sid=ebsco%3Aplink%3Ascholar\u0026amp;id=ebsco%3Agcd%3A180260329\u0026amp;crl=c\u0026amp;link_origin=scholar.google.com\u003c/li\u003e\n \u003cli\u003eTaylor, L., Gupta, V., \u0026amp; Jung, K. (2024). Leveraging visualization and machine learning techniques in education: a case study of k-12 state assessment data. \u003cem\u003eMultimodal Technologies and Interaction\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e(4), 28. https://www.mdpi.com/2414-4088/8/4/28\u003c/li\u003e\n \u003cli\u003ePhang, Z. B., Haw, S. C., Tai, T. E., \u0026amp; Ng, K. W. (2024, September). Interactive Data Visualization to Optimize Decision-Making Process. In \u003cem\u003e2024 International Symposium on Parallel Computing and Distributed Systems (PCDS)\u003c/em\u003e (pp. 1-6). IEEE. https://ieeexplore.ieee.org/abstract/document/10743427\u003c/li\u003e\n \u003cli\u003eOuyang, W. (2024). Data visualization in big data analysis: Applications and future trends. \u003cem\u003eJournal of Computer and Communications\u003c/em\u003e, \u003cem\u003e12\u003c/em\u003e(11), 76-85.\u003c/li\u003e\n \u003cli\u003eShahidan, N. F. A., Ibrahim, A. F., \u0026amp; Jamaluddin, M. N. F. (2024). Data Visualization of Student Academic Performance Analysis. \u003cem\u003eApplied Mathematics and Computational Intelligence (AMCI)\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(4), 49-61. https://ejournal.unimap.edu.my/index.php/amci/article/view/1476\u003c/li\u003e\n \u003cli\u003eOral, E., Chawla, R., Wijkstra, M., Mahyar, N., \u0026amp; Dimara, E. (2023). From information to choice: A critical inquiry into visualization tools for decision making. \u003cem\u003eIEEE Transactions on Visualization and Computer Graphics\u003c/em\u003e, \u003cem\u003e30\u003c/em\u003e(1), 359-369. https://ieeexplore.ieee.org/abstract/document/10292614\u003c/li\u003e\n \u003cli\u003eShinde, B. G., \u0026amp; Shivthare, S. (2024). Impact of data visualization in data analysis to improve the efficiency of machine learning models. \u003cem\u003eJournal of Advanced Zoology\u003c/em\u003e, \u003cem\u003e45\u003c/em\u003e, 107-112. https://shorturl.at/JGnD8\u003c/li\u003e\n \u003cli\u003eHossain, Q., Yasmin, F., Biswas, T. R., \u0026amp; Asha, N. B. (2024). Data-Driven Business Strategies: A Comparative Analysis of Data Science Techniques in Decision-Making. \u003cem\u003eSch J Econ Bus Manag\u003c/em\u003e, \u003cem\u003e9\u003c/em\u003e, 257-263. https://www.saspublishers.com/media/articles/SJEBM_119_257-263.pdf\u003c/li\u003e\n \u003cli\u003eUddin, M. K. S. (2024). A review of utilizing natural language processing and AI for advanced data visualization in real-time analytics. \u003cem\u003eGlobal Mainstream Journal\u003c/em\u003e, \u003cem\u003e1\u003c/em\u003e(4), 10-62304. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4993556\u003c/li\u003e\n \u003cli\u003eShahidan, N. F. A., Ibrahim, A. F., \u0026amp; Jamaluddin, M. N. F. (2024). Data Visualization of Student Academic Performance Analysis. \u003cem\u003eApplied Mathematics and Computational Intelligence (AMCI)\u003c/em\u003e, \u003cem\u003e13\u003c/em\u003e(4), 49-61. https://ejournal.unimap.edu.my/index.php/amci/article/view/1476\u003c/li\u003e\n \u003cli\u003eO\u0026rsquo;Shaughnessy, M., Glover, J., Hafizi, R., Barhi, M., Clowes, R., Chong, S. Y., ... \u0026amp; Cooper, A. I. (2024). Porous isoreticular non-metal organic frameworks. \u003cem\u003eNature\u003c/em\u003e, \u003cem\u003e630\u003c/em\u003e(8015), 102-108. https://www.nature.com/articles/s41586-024-07353-9\u003c/li\u003e\n \u003cli\u003eBach, B., Keck, M., Rajabiyazdi, F., Losev, T., Meirelles, I., Dykes, J., ... \u0026amp; Carpendale, S. (2023). Challenges and opportunities in data visualization education: A call to action. \u003cem\u003eIEEE Transactions on visualization and computer graphics\u003c/em\u003e, \u003cem\u003e30\u003c/em\u003e(1), 649-660. https://ieeexplore.ieee.org/abstract/document/10310184\u003c/li\u003e\n \u003cli\u003eChen, T., Liu, Y. X., Chen, T., Yang, M., Fan, S., Shi, M., ... \u0026amp; Huang, L. (2024). ImageGP 2 for enhanced data visualization and reproducible analysis in biomedical research. \u003cem\u003eImeta\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(5), e239. https://onlinelibrary.wiley.com/doi/full/10.1002/imt2.239\u003c/li\u003e\n \u003cli\u003eSotiropoulos, C., Giormezis, N., Pertsas, V., \u0026amp; Tsirkas, T. (2024). Biomarkers and data visualization of insulin resistance and metabolic syndrome: an applicable approach. \u003cem\u003eLife\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(9), 1197. https://www.mdpi.com/2075-1729/14/9/1197\u003c/li\u003e\n \u003cli\u003eZheng, M., Lillis, D., \u0026amp; Campbell, A. G. (2024). Current state of the art and future directions: Augmented reality data visualization to support decision-making. \u003cem\u003eVisual Informatics\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e(2), 80-105. https://www.sciencedirect.com/science/article/pii/S2468502X24000202\u003c/li\u003e\n \u003cli\u003eRomero-Organvidez, D., Horcas, J. M., Galindo, J. A., \u0026amp; Benavides, D. (2024). Data visualization guidance using a software product line approach. \u003cem\u003eJournal of Systems and Software\u003c/em\u003e, \u003cem\u003e213\u003c/em\u003e, 112029. https://www.sciencedirect.com/science/article/pii/S0164121224000724\u003c/li\u003e\n \u003cli\u003eYin, W., Hu, Q., Liu, W., Liu, J., He, P., Zhu, D., \u0026amp; Kornejady, A. (2024). Harnessing Game Engines and Digital Twins: Advancing Flood Education, Data Visualization, and Interactive Monitoring for Enhanced Hydrological Understanding. \u003cem\u003eWater\u003c/em\u003e, \u003cem\u003e16\u003c/em\u003e(17), 2528. https://www.mdpi.com/2073-4441/16/17/2528\u003c/li\u003e\n \u003cli\u003eMehrotra, S., Rangaiah, B., \u0026amp; Kathi, S. (2022). Relationship between decision-making, time perspective and stress. \u003cem\u003eTiming \u0026amp; Time Perception\u003c/em\u003e, \u003cem\u003e12\u003c/em\u003e(1), 47-63. https://brill.com/view/journals/time/12/1/article-p47_005.xml\u003c/li\u003e\n \u003cli\u003eThen, S. N., \u0026amp; Bigby, C. (2024). Supported decision-making and the Disability Royal Commission. \u003cem\u003eResearch and Practice in Intellectual and Developmental Disabilities\u003c/em\u003e, \u003cem\u003e11\u003c/em\u003e(1), 86-106. https://www.tandfonline.com/doi/full/10.1080/23297018.2024.2330961\u003c/li\u003e\n \u003cli\u003eAluja, A., Balada, F., Garc\u0026iacute;a, O., \u0026amp; Garc\u0026iacute;a, L. F. (2024). Psychometric study of two decision-making measures: The melbourne decision-making questionnaire versus the general decision-making style questionnaire. \u003cem\u003ePsychiatry International\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e(3), 503-514. https://www.mdpi.com/2673-5318/5/3/36\u003c/li\u003e\n \u003cli\u003eD\u0026rsquo;Alessio, I., Aitella, U., Giannini, A. M., \u0026amp; Burrai, J. (2024). \u0026ldquo;What about Military Decision-Making?\u0026rdquo;: A Bibliometric Review of Published Articles. \u003cem\u003eBehavioral Sciences\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(7), 514. https://www.mdpi.com/2076-328X/14/7/514\u003c/li\u003e\n \u003cli\u003eSun, H. Y., Xiao, Y. T., \u0026amp; Yang, S. S. (2024). The group intertemporal decision-making process. \u003cem\u003eBehavioral Sciences\u003c/em\u003e, \u003cem\u003e14\u003c/em\u003e(9), 815. https://www.mdpi.com/2076-328X/14/9/815\u003c/li\u003e\n \u003cli\u003eKarcılı, I., \u0026amp; Sevim, S. (2024). The effect of argumentation-based sociobiological topic teaching on 7th grade students\u0026apos; argumentation levels, decision-making skills and decision-making styles. \u003cem\u003ePamukkale Universitesi Egitim Fakultesi Dergisi-Pamukkale University Journal of Education\u003c/em\u003e. https://gcris.pau.edu.tr/bitstream/11499/57389/1/10.9779-pauefd.1435514-3722431.pdf\u003c/li\u003e\n \u003cli\u003eKollar, J. (2024). Decision-making on the job choice in the condition of Slovak households. https://naos-be.zcu.cz/server/api/core/bitstreams/5b1ec474-441d-4f5b-83f4-75e80823d41e/content\u003c/li\u003e\n \u003cli\u003eZaheer, R., Hanif, M. K., Sarwar, M. U., \u0026amp; Talib, R. (2025). Evaluating the Effectiveness of Dimensionality Reduction on Machine Learning Algorithms in Time Series Forecasting. \u003cem\u003eIEEE Access\u003c/em\u003e. https://ieeexplore.ieee.org/abstract/document/10929010\u003c/li\u003e\n \u003cli\u003ePham, D. L., Gillette, A. A., Riendeau, J., Wiech, K., Guzman, E. C., Datta, R., \u0026amp; Skala, M. C. (2025). Perspectives on label-free microscopy of heterogeneous and dynamic biological systems. \u003cem\u003eJournal of Biomedical Optics\u003c/em\u003e, \u003cem\u003e29\u003c/em\u003e(S2), S22702-S22702. https://www.spiedigitallibrary.org/journals/journal-of-biomedical-optics/volume-29/issue-S2/S22702/Perspectives-on-label-free-microscopy-of-heterogeneous-and-dynamic-biological/10.1117/1.JBO.29.S2.S22702.short\u003c/li\u003e\n \u003cli\u003eGrolli, R. E., Fabrizzio, G. C., Cabral, E. C., de Souza, J. M., de Souza Vieira, L., Zambeli, A. S., ... \u0026amp; Zibetti, A. W. (2025). Predictive tools in intensive care unit management: a protocol of a scoping review. \u003cem\u003eJournal of Medical Artificial Intelligence\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e. https://jmai.amegroups.org/article/view/9771/html\u003c/li\u003e\n \u003cli\u003eSharma, R. M. (2025). Artificial intelligence in medical image analysis and molecular diagnostics: recent advances and applications. \u003cem\u003eJournal of Medical Artificial Intelligence\u003c/em\u003e, \u003cem\u003e8\u003c/em\u003e. https://jmai.amegroups.org/article/view/10103/html\u003c/li\u003e\n \u003cli\u003eShah, R., Ali, S., Raziq, F., Ali, S., Ismail, P. M., Shah, S., ... \u0026amp; Qiao, L. (2023). Exploration of metal organic frameworks and covalent organic frameworks for energy-related applications. \u003cem\u003eCoordination Chemistry Reviews\u003c/em\u003e, \u003cem\u003e477\u003c/em\u003e, 214968. https://www.sciencedirect.com/science/article/abs/pii/S001085452200563X\u003c/li\u003e\n \u003cli\u003eMildau, K., Ehlers, H., Meisenburg, M., Del Pup, E., Koetsier, R. A., Ortega, L. R. T., ... \u0026amp; van der Hooft, J. J. (2025). Effective data visualization strategies in untargeted metabolomics. \u003cem\u003eNatural Product Reports\u003c/em\u003e, \u003cem\u003e42\u003c/em\u003e(6), 982-1019. https://pubs.rsc.org/en/content/articlehtml/2024/np/d4np00039k\u003c/li\u003e\n \u003cli\u003eChauhan, M., \u0026amp; Shiaeles, S. (2023). An analysis of cloud security frameworks, problems and proposed solutions. \u003cem\u003eNetwork\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(3), 422-450. https://www.mdpi.com/2673-8732/3/3/18\u003c/li\u003e\n \u003cli\u003eBruch, E., \u0026amp; Feinberg, F. (2017). Decision-making processes in social contexts. \u003cem\u003eAnnual review of sociology\u003c/em\u003e, \u003cem\u003e43\u003c/em\u003e(1), 207-227. https://www.annualreviews.org/content/journals/10.1146/annurev-soc-060116-053622\u003c/li\u003e\n \u003cli\u003eBajracharya, S., Carenini, G., Chamberlain, B., Chen, K., Klein, D., Poole, D., ... \u0026amp; \u0026Ouml;berg, G. (2018). Interactive visualization for group decision analysis. \u003cem\u003eInternational Journal of Information Technology \u0026amp; Decision Making\u003c/em\u003e, \u003cem\u003e17\u003c/em\u003e(06), 1839-1864. https://www.worldscientific.com/doi/abs/10.1142/S0219622018500384\u003c/li\u003e\n \u003cli\u003ePadilla, L. M., Creem-Regehr, S. H., Hegarty, M., \u0026amp; Stefanucci, J. K. (2018). Decision making with visualizations: a cognitive framework across disciplines. \u003cem\u003eCognitive research: principles and implications\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(1), 29. https://link.springer.com/article/10.1186/s41235-018-0120-9\u003c/li\u003e\n \u003cli\u003eBurnay, C., Dargam, F., \u0026amp; Zarate, P. (2019). Data visualization for decision-making: an important issue. \u003cem\u003eOperational Research\u003c/em\u003e, \u003cem\u003e19\u003c/em\u003e(4), 853-855. https://link.springer.com/article/10.1007/s12351-019-00530-z\u003c/li\u003e\n \u003cli\u003eCohen, D. J., Wyte-Lake, T., Canfield, S. M., Hall, J. D., Steege, L., Wareg, N. K., \u0026amp; Koopman, R. J. (2022). Impact of home blood pressure data visualization on hypertension medical decision making in primary care. \u003cem\u003eThe Annals of Family Medicine\u003c/em\u003e, \u003cem\u003e20\u003c/em\u003e(4), 305-311. https://www.annfammed.org/content/20/4/305?2023/7/20/?2023/7/20/\u003c/li\u003e\n \u003cli\u003eEcheverria, V., Martinez-Maldonado, R., Shum, S. B., Chiluiza, K., Granda, R., \u0026amp; Conati, C. (2018). Exploratory versus explanatory visual learning analytics: Driving teachers\u0026rsquo; attention through educational data storytelling. \u003cem\u003eJournal of Learning Analytics\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e(3), 73-97. https://research.monash.edu/en/publications/exploratory-versus-explanatory-visual-learning-analytics-driving-\u003c/li\u003e\n \u003cli\u003eLiu, S., Miao, H., Li, Z., Olson, M., Pascucci, V., \u0026amp; Bremer, P. T. (2024, June). AVA: towards autonomous visualization agents through visual perception‐driven decision‐making. In \u003cem\u003eComputer Graphics Forum\u003c/em\u003e (Vol. 43, No. 3, p. e15093). https://onlinelibrary.wiley.com/doi/abs/10.1111/cgf.15093\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Johannesburg","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"data visualization, learning analytics, decision-making, dashboards, systematic review, education, business intelligence, cognitive load","lastPublishedDoi":"10.21203/rs.3.rs-7560670/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7560670/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eData visualization (DV) and learning analytics (LA) play a critical role in simplifying complexity, enhancing interpretation, and supporting evidence-based decision-making across educational, business, healthcare, and policy domains. Despite the rapid growth of research between 2015\u0026ndash;2025, gaps remain in methodological transparency, tool adoption, and balanced reporting of advanced visualization techniques. This review systematically examines DV and LA literature to (i) assess trends in publication outputs and geographical contributions, (ii) identify the most frequently applied databases, tools, and visualization techniques, (iii) analyze decision-making outcomes and cognitive load implications, (iv) map target user groups, and (v) highlight persistent challenges and limitations constraining the field. A systematic search of Google Scholar, Scopus, and Web of Science yielded 101,685 initial records. After duplicate removal and screening, 123 studies were included for full analysis. Studies were classified into categories of visualization tools, techniques, application domains, and decision-making outcomes. Descriptive statistics and thematic synthesis were applied, and results are reported with visual summaries. Research outputs show steady growth with peaks in 2021\u0026ndash;2024, dominated by journal articles (69.92%) and contributions from the United States (24.39%), China (18.70%), and India (10.57%). The most frequently used databases were Google Scholar (52.03%), Scopus (30.08%), and Web of Science (17.89%). Tool distribution highlighted the dominance of Tableau (44.72%), Power BI (14.63%), and Excel (8.94%), while dashboards (26.83%), bar graphs (16.26%), and line graphs (12.20%) were the most reported visualization techniques. Education (43.09%) and business (39.84%) emerged as the leading domains of application, with decision-making outcomes most often improving business/industry performance (30%) and policy or healthcare (15% each). Cognitive load findings revealed a balance between reduction strategies (25%) and risks of complexity (20%), underscoring design trade-offs. User groups were led by analysts (32.52%), managers (19.51%), and researchers/students (17.07% each). Key limitations included complexity and scalability (20%), interpretability issues (18%), and data integration challenges (15%). The evidence demonstrates that DV and LA provide significant pedagogical, operational, and strategic benefits. However, reliance on dashboards and descriptive methods reflects underutilization of advanced predictive or interactive approaches. Addressing methodological transparency, scalability, and user training will be essential for broader adoption. A framework (Fig.\u0026nbsp;18) is proposed to integrate inputs, context, methods, mechanisms, users, and boundaries, offering a structured path toward advancing the role of DV and LA in educational decision-making.\u003c/p\u003e","manuscriptTitle":"Tools, Techniques, and Applications of Data Visualization in Education and Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 06:07:05","doi":"10.21203/rs.3.rs-7560670/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"64b2bc7b-79dc-4c67-8d0e-ae4054e286a0","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54336869,"name":"Educational Philosophy and Theory"},{"id":54336870,"name":"Educational Psychology"},{"id":54336871,"name":"Special Education"},{"id":54336872,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-09-09T06:07:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-09 06:07:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7560670","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7560670","identity":"rs-7560670","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}