Employing Network Analysis of Big Data on Platform (X) in Relation to Saudi Vision 2030 (An Analytical Longitudinal Study for the Period from 2016–2022)

Employing Network Analysis of Big Data on Platform (X) in Relation to Saudi Vision 2030 (An Analytical Longitudinal Study for the Period from 2016–2022) | 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 Research Article Employing Network Analysis of Big Data on Platform (X) in Relation to Saudi Vision 2030 (An Analytical Longitudinal Study for the Period from 2016–2022) Mohammad Ali This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7482610/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 This study aimed to explore how artificial intelligence techniques can be utilized in the analysis of big data in relation to Saudi Vision 2030. Using methodologies such as network analysis and sentiment analysis, the study sought to provide in-depth insights into how Saudi Vision 2030 is perceived by the Saudi public, and to identify the aspects that garner the highest levels of attention, interaction, and engagement. The study focused on the Arabic hashtag (رؤية_السعودية_2030#) and the English hashtag (#SaudiVision2030) on the X platform, covering a seven-year period from 2016 to 2022. A mixed-method approach was adopted, combining traditional statistical analysis with network analysis techniques and natural language processing — using artificial intelligence tools — to gain a deeper understanding of public sentiment and the dominant topics in discussions surrounding Saudi Vision 2030. Tweets were categorized by sentiment into positive, negative, and neutral in order to assess the overall public mood toward the Vision and its diverse and comprehensive developmental goals, which fundamentally emphasize sustainability. Textual network analysis helped explore relationships among user opinions and responses to the Vision. The findings revealed that positive sentiment towards Vision 2030 programs was predominant, accounting for 50.3% of tweets, compared to 37% neutral and 12.6% negative sentiment. This indicates widespread support within Saudi society for the Vision and the economic, social, and cultural transformations it has introduced, all of which contribute to sustainable development. The study recommended the use of Large Language Models (LLMs) for big data analysis on social media platforms instead of traditional classification models, due to their superior capabilities in interpreting text and language. It also advised the application of Knowledge Graphs to represent and extract information from textual data, as this approach provides a clearer and more accurate representation of network relationships. Saudi Vision 2030 network analysis artificial intelligence sentiment analysis mixed-method analysis Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 1- Introduction In recent years, there has been growing interest in social networks and virtual communities, especially as the Internet has become the ideal platform for forming such communities and reaching millions of people in remarkable ways. The Internet and its interactive features have become an essential part of daily life for individuals and groups. The term "virtual community", once a subject of scholarly attention, has now become a widespread and commonly understood concept—not only in academic studies but also among Internet users in general (Zaki, 2015). With the evolution and expansion of virtual communities, new theories and concepts have emerged that re-evaluate many ideas related to media and communication. Additionally, the significant progress in the use of social networks has contributed to shaping theoretical frameworks and research methodologies related to these platforms (Sanousi, 2021 ). As a result of the rapid advancements in online communication, social media platforms now offer users highly interactive environments that transcend geographical boundaries, attracting the time and attention of young people in particular, and all age groups in general. These platforms allow individuals to share personal experiences and engage in rich social interaction, integrating personal, interpersonal, group, and public communication into a unified environment that is reshaping their social and communicative structures (Tosun, 2012 ). This virtual interaction can be observed in public discourse on Saudi Vision 2030, a strategic framework for national development, as seen in discussions on the platform X using the hashtags “#SaudiVision2030” and “#رؤية_السعودية_2030”. This study covers the period from the initial use of these hashtags on April 21, 2016, through the end of 2022, capturing a range of public perspectives. The official announcement of Vision 2030 was made through the “SaudiVision2030” account on April 25, 2016. This study aims to bridge the gap between public perception and the broader context of sustainability. By interpreting sentiments and prevailing themes in discussions on Platform X, it seeks to contribute to a deeper understanding of how Vision 2030 is viewed in relation to global sustainability efforts and its potential impact on achieving various Sustainable Development Goals (SDGs). The conversations reflected in these tweets provide a unique insight into public mindset, revealing how different aspects of Vision 2030 are perceived locally. Analyzing this discourse offers valuable insights into collective sentiment toward the Vision’s sustainability initiatives—particularly relevant given the alignment between Vision 2030’s objectives and the SDGs, such as expanding renewable energy, encouraging economic diversification, and enhancing social well-being. The sentiments and topics expressed by X platform users reflect not only immediate responses to these initiatives but also offer a forward-looking perspective on the area’s most likely to gain public support. Understanding this digital discourse is vital for assessing the sustainability of Vision 2030. It helps identify areas where public awareness or engagement may need to be strengthened, and where communication strategies might require adjustment to better align with public expectations. Thus, the study moves beyond basic sentiment analysis to develop a deeper understanding of how the narrative surrounding sustainable development within Vision 2030 is being shaped through social dialogue, ultimately influencing public opinion and potentially the trajectory of achieving the SDGs. Drawing upon the scholarly theories, prior research, and the interdisciplinary methodology of Social Network Analysis (SNA)—which reveals the structure of relationships among social entities and how these structures impact other social phenomena—the study investigates the patterns of interaction among actors (tweeters). SNA is a robust framework to analyze social behavior, online communication within groups, and networked relationships across social networks. This study, therefore, applies network analysis techniques to big data from the Platform X regarding Saudi Vision 2030. The analysis is conducted as a longitudinal study from 2016 to 2022. 2. Literature Review A review of prior research indicated into three main categories. 2.1 Studies Addressing Artificial Intelligence Technologies Previous studies have focused on the scholarly legacy concerning the application of artificial intelligence (AI) technologies in media and social networks, particularly in network analysis, while also exploring the role of social media platforms in supporting the goals of Saudi Vision 2030. Given their widespread influence and reach, social media platforms have gradually shaped individuals’ perceptions by serving as trusted sources of data. Social media, especially microblogging sites such as Platform X , have a significant influence on public opinion, functioning as influential information sources even for those not actively seeking news, who may come across it through friends’ activities or casual discussions (Johnson, et al., 2015; Kümpel, A. S., 2020). The growing capabilities of machine learning algorithms, particularly in natural language processing (NLP), have demonstrated efficiency in analyzing large datasets, making them essential tools for extracting insights from big data in social networks. NLP has undergone a major transformation due to the emergence of Transformer models, which marked a significant leap by enabling more accurate, large-scale understanding and processing of language. The role of social media in shaping news engagement has become more evident. Platforms like X (formerly Twitter) are not only channels for disseminating news but also influential tools for enhancing user engagement and interaction. These platforms help in forming public awareness and perceptions regarding specific issues, based on how content is presented and how users engage with it—highlighting the pressing need to understand how social media affects news dissemination and interaction (Kümpel, A. S., 2020). The importance of topic modeling in sentiment analysis on social media is evident in a study titled "Sentiment Analysis in Social Networks through Topic Modeling" , which applied the Latent Dirichlet Allocation (LDA) algorithm to explore topic distribution in conversations and connect them with various sentiments. This approach enables the identification of user groups or sub-communities within the network and the assessment of how affiliation affects user sentiments. It provides deeper insight into how topics and emotions interact within social networks and how sentiments and themes are distributed across them (Naskar et al., 2016 ). Similarly, Abdulhamid (2020) confirmed the effectiveness of AI in journalistic work—especially the use of bots for covering economic, sports, and weather news. Such bots can be programmed for automated conversations on websites and social media, big data processing, and machine translation. The study's results also emphasized the importance of AI in improving the structure and quality of media content. Cheng ( 2018 ) explored how AI techniques and algorithms could help media professionals better understand their audiences, their preferences, and their reactions to displayed content—thus enabling them to provide content that meets audience satisfaction through tailored applications and multimedia interfaces. The study suggested that audiences tend to focus on news relevant to their personal lives and interests and dismiss irrelevant information. Amato et al. ( 2019 ) conducted a study to explore AI tools in media production, highlighting their potential to enrich the media industry, especially visual media—towards greater creativity. AI enables functions such as content-based image retrieval, image annotation, and user-preference-based image searches. Such capabilities provide media professionals with diverse options for producing creative visual content. Harfoush et al. ( 2019 ) emphasized the role of robot journalism in influencing the media profession. It predicted that robot anchors could potentially replace human anchors in the future. Robot anchors are expected to carry semantic and implicit dimensions and contribute to enhancing the media field. Al-Ezza (2017) confirmed that modern television technologies have boosted viewship for news programs, but raised concerns among media professionals about AI developments, which take two main forms: first, to the replacement of human job functions by AI systems capable of performing tasks with high efficiency, lower risk, and minimal cost; and second, the potential loss of human control as AI systems increasingly participate in decision-making . Regarding future AI adoption over the next decade (2021–2031). Ibrahim ( 2022 ) revealed that most respondents indicated economic factors as the most influential in adopting AI in Palestinian satellite channels. This is because technological transformation requires substantial financial resources. Professional factors such as staff training and qualification were also highlighted. Similarly, Mansour et al. (2017) in "The Future of Data Journalism in Egypt (2017–2037)" found that the main obstacle to data journalism is the lack of qualified media professionals capable of using and applying data journalism. However, the motivation behind employing data journalism lies in improving journalistic content to attract audiences and meet the evolving demands of the digital era by incorporating data into journalistic storytelling. 2.2 Studies on Sentiment Analysis and Big Data Sentiment analysis, based on opinion mining and affective computing theories, has become widely used to gauge public mood and measure trends across various domains such as marketing, politics, and social media research. Sentiment analysis is a subfield of natural language processing (NLP) that involves identifying and classifying opinions expressed in text to determine the writer's stance toward a particular topic. This study relies on BERT models for sentiment analysis, leveraging their advanced understanding of linguistic context and details. BERT enables more accurate and context-aware analysis by processing text bidirectionally—unlike traditional models that process text sequentially. Several studies have applied sentiment analysis, such as Elshereef ( 2022 ), which analyzed sentiments in tweets during the 2020 U.S. presidential elections. The study found that both candidates received similar levels of positive and negative opinions, with a sentiment classification difference of less than 1% favoring Biden—who received slightly more positive sentiment than Trump. This was later confirmed by the actual election results. These findings suggest that sentiment analysis using big data from Twitter can serve as a precise and cost-effective tool for measuring public opinion toward candidates and predicting election outcomes. Faraj ( 2022 ) examined the utilization of big data to improve search and retrieval mechanisms and personalize services in information institutions, using a foresight-based approach. It revealed that big data management in these institutions undergoes stages of data collection, flow, storage, display, and analysis. These processes aim to enhance search capabilities and service personalization and help overcome challenges posed by content from various digital repositories. The study emphasized the potential of big data systems to offer rich search experiences and services that meet user informational needs. It employed a descriptive methodology, focusing on content analysis, and reviewed global best practices in information institutions. Thabet et al. (2022) explored the impact of big data analysis on the operational efficiency of banks using Data Envelopment Analysis (DEA). The results indicated that one of the main reasons for low bank efficiency was the decline in non-interest income. However, big data analysis had a positive impact on efficiency scores, confirming that the bank succeeded in adopting a suitable financial technology strategy. The study emphasized the importance of integrating internal bank data with insights derived from big data analysis. El-Sayed ( 2021 ) investigated the use of AI applications for real-time sentiment analysis of social media users during the COVID-19 pandemic. The results showed that most digital citizens expressed negative sentiments toward the virus on Twitter, with fear being the dominant emotion. Using topic modeling, COVID-19-related tweets were categorized into five main themes: healthcare environment, emotional and psychological support, business economy, social change, and psychological stress. The study concluded that (a) Twitter can serve as a promising entry point to reflect public awareness, (b) Tweets can be used to monitor the intensity of crises over time, and (c) Sentiment analysis confirms the effectiveness of geotagged tweet messages in identifying regions most affected by the crisis. Al-Areeshi & Saleh ( 2020 ) explored the use of big data and AI in COVID-19 pandemic. It concluded that deep learning techniques could process CT scan images by training models on relevant datasets, enabling rapid diagnosis and decisions regarding quarantine or medical treatment—thus accelerating response measures. Badran ( 2019 ) investigated the impact of big data analytics on marketing campaign efficiency through a case study of Syriatel. The study concluded that the speed of data analysis via a big data platform directly influenced campaign performance. The platform allowed the analysis of millions of records and generated user features, including predicting customer churn. The company developed an integrated system covering all data lifecycle stages—from collection to processing, analysis, storage, and web interfaces designed for ease of use by professionals. A study by Zaki et al. (2016) introduced a sentiment analysis system for Arabic news and articles, known as SASAN . It focused on opinion mining within Arabic news and articles to extract direct sentiment at the article level. Given the length of articles, the researchers proposed a novel methodology first to identify opinion sentences related to the article's main goal. They used machine learning and Typed Dependency Relations (TDR) to extract such sentences, identifying those with high-frequency nouns or adjectives as target sentences. They then built a sentiment lexicon using machine learning, based on a dataset covering fields like politics, economy, government, sports, and arts. Three methods were used for sentiment extraction: lexicon-based, machine learning-based, and opinion sentence extraction. The study concluded that the machine learning-based lexicon approach (using SVM and TDR) yielded the most effective results. 3.3 Studies Addressing Saudi Vision 2030 The Kingdom of Saudi Arabia has adopted Vision 2030, which aims to build the necessary capacities and capabilities to achieve the Kingdom’s ambitious goals by launching 13 developmental programs. These programs serve as a roadmap for economic and developmental work across all fields. The vision outlines the Kingdom’s general directions, goals, and commitments to build a vibrant society, a thriving economy, and an ambitious nation. This was highlighted in a study by Al-Thaqafi ( 2020 ), which noted that the newspapers analyzed in his study showed interest in issues related to human empowerment and in shaping new horizons for Saudi society. Many media and communication experts indicate that social networks are the fastest means of communication in attracting millions of members and users over recent years. These platforms emerged in the early years of this century, reflecting their ability to meet the diverse communication needs of various user groups (Statistics, 2016 ). This was confirmed by Al-Qahtani (2019), which concluded that social media is one of the most important means of communication in Saudi society today, as it facilitates the dissemination of news from multiple sources. This aligns with Al-Zahrani & Salem (2019), which found that the main reasons young people rely on social media to obtain information about Vision 2030 are the ease of accessing information, followed by the ability to comment, participate, and share their views. Several outcomes have resulted from young Saudis following social media coverage of the Vision, including supporting for state’s reform measures, increasing awareness and perception, and fostering a desire to participate. Electronic journalism is among the new communication means preferred by Saudi society. Al-Toukhi ( 2018 ) indicated that the electronic newspapers followed the most by Saudi university students included Sabq , Okaz , Ajil , Al-Wiam , and Al-Riyadh . Ben Labda’s study (2018) investigated the role of social media in shaping political awareness of Vision 2030 among the public from the perspective of Saudi experts and specialists. The study explored the sources that Saudis rely on to obtain information about the government’s future goals, the implementation stages, the competent authorities, and the future priorities for Saudi Arabia. In the same vein, Alkathiri, ( 2020 ) revealed a positive relationship between the Saudi government’s use of social media and its influence in convincing Saudi citizens of Vision 2030. The majority of survey participants agreed that the Saudi government uses new media to persuade public opinion to trust Vision 2030. Furthermore, Alsaaidi ( 2020 ) examined the Saudi government’s approach in using a national branding promotion strategy and presenting various values related to Vision 2030 via social media as a means of interaction with the world, specifically through platform (X). The researcher analyzed tweets related to the national brand of Vision 2030 posted on the account (2030SaudiVision). The results of 2,117 tweets revealed the Kingdom’s tendency to use platform (X) as a trusted tool for promoting Vision 2030 and enhancing its position on the world stage. Knowledge Gap A review of previous literature shows that the social network analysis is an emerging methodology that has gained considerable attention in international academic circles, but less in the Arab world. This multidisciplinary methodology uses a range of algorithms, including artificial intelligence for qualitative content analysis and analytical algorithms for detecting relational networks, making it suitable for interdisciplinary media studies. However, higher education institutions and academic departments in Arab universities have been slow to adopt such advanced methodologies, especially in the field of digital media. Most earlier studies have relied on quantitative content analysis tools to investigate digital content on various platforms, whereas this study employs social network analysis methodology to analyze big data from platform (X), formerly known as Twitter. The current study aims to expand the use of machine learning strategies, mainly sentiment analysis, which can provide significant insights into social media trends. Network analysis can offer explanations for topics instead of focusing solely on the emotional content of online conversations. Network analysis identifies topics that stimulate user interaction on platform (X) regarding Vision 2030 programs. This study will provide comprehensive and precise insights into Saudi Vision 2030 programs. This approach will significantly contribute to understanding the relationship between events and social media discourse, highlighting the power and potential of advanced machine learning techniques in the era of big data and artificial intelligence algorithms. The current research aligns with studies by Elshereef ( 2022 ) and Zeki (2016) in relying on sentiment analysis tools. These studies confirm that opinion mining and sentiment analysis are more effective when based on opinion lexicons and machine learning methods, emphasizing their value in assessing the positive and negative sentiments expressed by social network users. Research Questions What are the characteristics and content of the hashtags that addressed Saudi Vision 2030 during the study period? What are the main topics included in the tweets' hashtags related to Saudi Vision 2030 during the study period? What sentiment trends are reflected in users’ engagement with the hashtags of Saudi Vision 2030 during the study period? What network relationships emerge from users' sentiments in the hashtags of Saudi Vision 2030 during the study period? What network relationships emerge from the sentiments expressed through emojis in Saudi Vision 2030 hashtags during the study period? What are the methodological steps involved in conducting social network analysis in this study? 3. Theoretical Framework 3.1 Network Theory Many theorists in the field of media and communication, as well as in the broader social sciences, emphasize the need for advanced research tools to study social networks. Among these tools is social network analysis- described not as a standalone theory, but rather as a methodology. Network theory is considered a fundamental part of graph theory, which, in computer science and network sciences deals with the study of graphs as representations of information and symmetrical or asymmetrical relationships between discrete entities. The theory is referred to as the network approach, social network analysis, or network representation, all derived from computer science. It has been used in the field of new media to describe and diagnose forms of online social networking, to identify the relationships that connect citizens with new technologies, and to better understand contemporary social and cultural changes in light of the concepts of individualism and decentralization. In this study, network theory is applied to analyze and examine complex social structures with broad applications, including the use of various graph types, and advanced computational techniques through which the relational patterns of nodes—representing hashtags in tweets—and links, i.e., connections, are analyzed based on mathematical calculations. These calculations yield metrics for network structure or parameters that define the characteristics of network activity, social roles, and levels of participation. The primary purpose of network analysis lies in uncovering the types of connections between hashtags, identifying benefits and constraints, and understanding the overall network structure. It also focuses on network properties while taking into account that this network analysis may contribute to the construction of scenarios based on the patterns of connections and nodes across groups. 3.2 Sentiment Analysis Sentiment Analysis is a branch of Natural Language Processing (NLP) that involves identifying and classifying opinions expressed in text to identify the writer’s stance toward a particular subject. The current study draws on BERT models for sentiment analysis, benefiting from its advanced understanding of language context and nuances. BERT (Bidirectional Encoder Representations from Transformers) enables more accurate and context-aware analysis by processing the text bidirectionally, unlike traditional models that read the text sequentially. Sentiment analysis, grounded in opinion mining and affective computing theories, is widely used to gauge general mood in diverse fields such as marketing, politics, and social media analysis. The levels of sentiment analysis, according to text output, are divided as follows. (Md Suhaimin et al., 2023 ). Document-level sentiment analysis refers to analyzing the writer’s emotions and detecting feelings such as anger, joy, etc. Fine-grained sentiment analysis refers to analyzing the resulting and reflected sentiments from the text: positive, negative, and neutral. Aspect-based sentiment analysis refers to the opinions the writer focused on in a particular aspect of the document rather than others. Lexicon-based sentiment analysis refers to building an opinion lexicon to understand others' intentions toward the document topic through expressive words in the text. The stages, techniques, and tools of sentiment analysis vary. The main steps in conducting research according to sentiment analysis are as follows (Al-Khalifi, 2019 ). Collecting data from social media platforms. Preparing and preprocessing data using NLP techniques. Applying algorithms to perform analysis and extract the opinions or sentiments within subjective texts and determine their polarity. Presenting results using charts and graphs. 3.3 Study Terminologies Social Network Analysis : A mixed method, interdisciplinary approach used to uncover the structure of relationships between social entities and examine the influence of these structures on other social phenomena. It investigates patterns of social relationships between actors (users) by mapping and measuring the connections and flows between people, groups, organizations, computers, websites, and other knowledge-processing entities. In this framework, nodes/vertices represent individuals, while edges/links represent the relationships or flows between them. In short, social network analysis provides both a visual and mathematical representation of human relationships, along with an analysis of social media content and the sentiments embedded within it. Sentiment Analysis : A branch of NLP that involves identifying and classifying opinions expressed in text to determine the writer’s position toward a specific topic. Social Media Analysis : Drawing on theories related to social networks and their influence on public opinion; social media analysis seeks to understand the dynamics of online communities and dissemination of information. On platforms such as X (formerly Twitter), real-time information sharing generates vast volumes of data that are ideal for sentiment and public discourse studies. The size and diversity of tweets make this approach particularly effective for capturing immediate reactions and tracking the evolution of narratives about major events. 4. Methodology 4.1 Type of Study This study is classified as descriptive-explanatory research that aims to conduct a network analysis of big data from the (X) platform regarding Saudi Vision 2030. It combines traditional statistical methods to analyze data from a quantitative perspective (e.g., frequencies, numerical measures) with AI tools and algorithms to examine data from a qualitative perspective (e.g., sentiment analysis of textual data). This includes techniques such as data mining, text mining, social media mining, and opinion mining. These methods are adopted due to the fact that the primary dataset is large-scale and massive, making it difficult to extract meaningful information and insights using traditional methods (Azzalini & Scarpa, 2012 ). There is still no universally accepted process for scientific structural analysis, as the steps involved can vary by case and by analyst (Sharda et al., 2020). However, certain steps, such as data collection and data preprocessing, are essential in most analyses. These steps can differ and reveal the unique structure of each study (Kumar et al., 2014 ). Often, the source of textual data includes social media posts, comments, academic articles, blogs, and other online content. 4.2 Study Approach The study adopted a mixed-methods approach within the framework of integrative research to analyze the data of the applied study. This approach adds greater depth to quantitative media research and enhances the objectivity of qualitative analysis, thereby helping to overcome the methodological limitations of each (Sawan, 2016). The quantitative approach was employed in the content analysis to calculate frequencies and percentages, while the qualitative approach was used through AI algorithms to identify sentiments and underlying topics in these tweets. The study also relied on the social network analysis (SNA) approach, which provides a number of modern tools for identifying the most trending and widely discussed issues. This allows tracking discussion topics and analyzing how they evolve over time. The SNA approach enables new analytical methods that are not easily achievable through traditional methodologies that rely on research tools such as interviews and observations. It has been developed to analyze virtual social structures. The importance of SNA lies in its ability to explain the reasons behind certain behaviors of network members. Understanding these behaviors is closely linked to other factors such as individual and group relationships, as well as the culture of society under study. This approach also helps in understanding the community dynamics resulting from interactions among its members, the influence of individuals on those around them in the network, and consequently, their cumulative impact on the network as a whole (Al-Shaddi, 2010 ). Study Population and Sample The population of the current study comprised of social media platforms. Platform (X), formerly known as Twitter, was selected from among social networking platforms for the analytical study for the following reasons: It is preferred by the Saudi society. According to a recent scientific study, 63% of the Saudi population use platform (X) daily as a source of information and for conducting searches. The Kingdom of Saudi Arabia ranks first globally in terms of the percentage of active users, with 41% of internet users in the country regularly tweeting on Platform (X). Platform (X) offers features such as retweeting, liking, replying, and displaying trendy hashtags on the user's homepage. This makes it easier for users to identify and engage with the most discussed topics. Unlike other platforms that do not display trending topics, Platform (X) enables users to see the conversation. Consequently, when a user logs into platform (X), they can easily see the issues occupying users' attention and then decide whether to participate in the discussion or simply observe. The study focused on two hashtags from the official account of Saudi Vision 2030 (SaudiVision2030), which was launched on April 25, 2016: The Arabic hashtag: "#رؤية_السعودية_2030", and the English hashtag: "#saudivision2030 ". The study extended over a period of 7 years, from April 25, 2016, to the end of 2022. The total number of tweets collected under these two hashtags was 266,991, of which 240,644 tweets were under the Arabic hashtag and 26,347 under the English one. In total, 20 related hashtags were selected for analyzing the sentiment trends of users regarding the Vision, as shown in the study tables. Additionally, 45 hashtags were included in the network analysis conducted throughout the entire 7-year period. 4.4 Data Collection Tools The study relied on tools and data collection through a subscription to the API of platform X, combined with custom Python scripts developed to retrieve the data. Due to the large volume of data, the processes of collection, filtering, and analysis lasted a full year. The analysis involved gathering data while emphasizing the critical importance of obtaining highly representative user data. These data—referred to as the data source in text mining—were extracted from microblogs, comments, academic articles, and social media content. A comprehensive dataset was collected from user tweets and their comments, along with associated features (time, likes, replies, retweets, location, etc.) for each tweet from the text-rich environment of the social media platform X. The dataset specifically included several hashtags mentioned within the tweets. Big data tools were used to overcome the limitations of storage and processing of the massive, diverse data volumes in social networks. This requires an integrated set of tools and procedures for handling big data, as outlined by (Ali, 2018 ): Data Mining Tools : Manage unstructured data such as text and user activity, which are distributed across various devices on the web. Data Analysis Tools : Apply methods such as comparison, classification, approximation, and correlation in order to reach the desired outcomes. Data Visualization Tools : Present final analysis results in visual and graphical form, based on the study’s predefined objectives. 4.5 Study Limitations Topical Scope: Limited to two hashtags from the official account of Saudi Vision 2030 (SaudiVision2030): the Arabic hashtag #رؤية_السعودية_2030, and the English "#saudivision2030". Temporal Scope: Covered a 7-year period, from April 25, 2016, to December 30, 2022. Spatial Scope: Restricted to interactions taken place on Platform (X), though the data included contributions from users worldwide. 4.6 Statistical Methods Due to the large volume of data, a variety of traditional, modern, and AI-based tools and algorithms were combined to analyze the data both quantitatively (frequencies and numerical data) and qualitatively (sentiment analysis). The Python programming language was the primary tool for analysis. 5.7 Methodological Procedures of the Study The researcher followed several methodological procedures to obtain the results, including data collection and preprocessing, sentiment analysis, and then converting the results extracted from qualitative analysis into quantitative form. Artificial intelligence models mentioned in the AI-related literature review were employed, specifically three sentiment analysis models, along with the parameters shown in Fig. 1 . 4.8 Steps of Data Collection and Processing In modern data analysis, whether in data mining, text mining, or social media mining, the primary data sources are often vast, posing significant challenges in extracting meaningful insights (Azzalini, et al, 2012). There is no universally accepted, unified process for analyzing the structure of mining methods; the problem-solving approach and its associated steps often vary from one case to another and from one analyst to another (Sharda et al., 2020). While essential steps such as data collection and preprocessing are critical prior to analysis, the inherent diversity in these steps may reveal unique structural characteristics for each study (Kumar et al., 2014 ). In this study, we used a sequential text analysis process to develop a social network analysis methodology that benefits from machine learning techniques, specifically supervised sentiment analysis, alongside algorithms such as network analysis to extract valuable insights from tweets (microblogs). Figure 1 illustrates the core stages of the current study’s methodology. The process began with data collection, with a focus on obtaining highly representative data that effectively captures users’ public opinions. In text mining, this corpus, referred to as the data source, may originate from microblogs, comments, academic articles, social media content, and other sources. For this study, a comprehensive set of user tweets and comments was extracted from the text-rich environment of the Twitter platform, along with associated metadata (such as date and time, likes, replies, retweets, links, and locations,) The dataset consisted of 134,147 tweets under the two hashtags (#رؤية_السعودية_2030 and #SaudiVision2030), with the earliest tweet dated April 21, 2016. The hashtags were officially adopted by the Vision’s account April 25, 2016, and data collection continued through the end of 2022. The second phase, data preprocessing, was essential to improve the data analysis. This phase holds significant importance because any errors made here—known as “systematic errors”—can have a negative impact on the analysis (Sharda et al., 2020). Preprocessing included the removal of empty tweets, duplicates, and tweets without any textual data, reducing the number of tweets to 108,436. Additional steps included removing emojis, replacing user mentions with the keyword “user,” and applying other standard preprocessing techniques. After the data was prepared, machine learning algorithms were applied for sentiment analysis. We used three transformer-based sentiment analysis models: the Camel BERT model for Arabic, and the Cardiff models for English and multilingual texts (Barbieri et al., 2020 ; Barbieri et al., 2022 ; Inoue et al., 2021 ). These models, along with appropriate text analyzers, converted the textual data into digital format, allowing effective sentiments classification of the tweets. 5. Results and Discussion 5.1 Results Table (1) Form of tweets about Saudi Vision 2030 during the study period Time period (2016) (2017) (2018) (2019) (2020) (2021) (2022) Total Form of Tweets Languages 1- Arabic 2- English 3- Urdu 4- Other Tweets 92272 12510 12608 12947 15368 43565 36403 225673 Accounts 40830 5444 4974 5194 6002 13213 8185 83842 Likes 313752 99697 127451 167224 170545 387958 445147 1711774 Replies 78864 22526 26850 51028 38534 73214 85810 376826 Retweets 651470 156726 135121 140390 123453 269221 283182 1759563 Interaction 1044086 278949 289422 358642 332532 730393 814139 3848163 Table (1) shows the format of tweets of Saudi Vision 2030 during the study period, represented by the number of tweets published from 2016 to 2022, totaling 225,673 tweets, posted by 83,842 accounts, with 1,711,774 likes, 376,826 replies, 1,759,563 retweets, and 3,848,163 total interactions. These tweets were written in four different languages over the course of the study. A closer look at the data in Table (1) reveals that the highest volume of tweets appeared in 2016, the launch year of Vision 2030, with 92,272 tweets, compared to only 12,510 tweets in 2017, which was the lowest number across the seven years studied. This spike in 2016 may be attributed to the intensive media campaigns that accompanied the launch of the Vision in its first year, along with strong public engagement and participation. The table also shows that the highest number of likes for Vision 2030 programs was in 2022, totaling 445,147 likes. This indicates positive outcomes and achievements seven years after the launch of the Vision. Similarly, the highest number of replies appeared in 2022, which suggests a more mature public understanding of the goals and programs of Vision 2030. On the other hand, the retweet peaked in 2016, totaling 651,470, reflecting strong public interaction and engagement with the Vision and its various programs. The overall interaction with the hashtags was especially notable in the first year of the Vision, reaching 1,044,086. Table (2) Multimedia content of tweets about Saudi Vision 2030 during the study period Time period (2016) (2017) (2018) (2019) (2020) (2021) (2022) Total Multimedia Content of Tweets Images 23184 6334 8375 8328 9052 28194 26143 109610 Videos 980 864 967 1117 1548 3672 3685 12833 Links 16805 3289 2923 2209 2833 12755 12627 53441 Mentions 15772 4368 7485 8425 10477 16168 14732 77427 Hashtags 10589 6419 7494 7198 10173 15766 13294 70933 Table (2) shows the multimedia content of tweets related to Saudi Vision 2030 during the study period. The total number of accompanying images in Vision 2030-related tweets reached 109,610 images, 12,833 video clips, 53,441 links and references to other web pages and sites, 77,427 user mentions, and 70,933 hashtags. A closer look at Table (2) shows that the most prominent use of images occurred during 2021 and 2022, indicating the multiplicity of projects implemented as part of Vision 2030 programs. This finding is further supported by the high number of video clips posted in the same period, totaling 3,672 videos in 2021 and 3,685 in 2022. Hashtag usage also reached its highest level in 2021 with 15,766 hashtags, followed by 13,294 hashtags in 2022, reflecting a peak in user engagement and dissemination of Vision 2030-related content during those years. Table (3) Hashtag data analyzed in the study Hashtags Raw Data Processed Data F % F % رؤية_السعودية_2030 240644 90.13 204791 90.75 Saudivision2030 26347 9.87 20882 9.25 Total 266991 100 225673 100 The data in Table (3) illustrates the hashtags analyzed on platform (X), specifically the hashtag (#رؤية_السعودية_2030). During the 7-year study period, the total number of tweets reached 266,991, of which 240,644 tweets (representing 90.13%) were under the Arabic hashtag (#رؤية_السعودية_2030), while 26,347 tweets (or 9.87%) were under the English hashtag (#Saudivision2030). Examining the data before the cleaning process reveals that there were 204,791 tweets under the Arabic hashtag (#رؤية_السعودية_2030), and 20,882 tweets under the English hashtag (#Saudivision2030). Table (4) Language used in tweets about Saudi Vision 2030 during the study period Language F % Arabic 210812 93.41 English 13363 5.92 Urdu 238 0.11 Other 1260 0.56 Total 225673 100 Table (4) shows the languages used in tweets posted under the Vision 2030 hashtags — #رؤية_السعودية_2030 (in Arabic) and #Saudivision2030 (in English) — on platform (X) during the study period from April 25, 2016, to December 31, 2022. Tweets were written in three main languages as follows: Arabic: 93.41% English: 5.92% Urdu: 0.11% Other languages: 0.56% This reflects the strong dominance of Arabic content in discussions around Saudi Vision 2030. Table (5) Sentiment orientation of tweets about Saudi Vision 2030 during the study period Sentiment F % Positive 113522 50,3 Negative 28468 12,6 Neutral 83683 37 Tota 225673 100 Table (5) presents the sentiment trends of tweets under the Saudi Vision 2030 hashtags. Positive sentiment ranked first, with 113,522 occurrences, representing 50.3% of the total. In comparison, neutral sentiment appeared 83,683 times (or 37%), while negative sentiment was the least frequent, with 28,468 occurrences (12.6%). These results indicate that positive sentiment dominates the tweets discussing Vision 2030 programs, suggesting broad public support for the initiative among Twitter users. Many individuals express their endorsement of Vision 2030 due to its ambitious goals focused on diversifying the economy, enhancing quality of life, and promoting social development. Positive engagement is especially evident in reaction to major initiatives launched under the Vision such as the NEOM and Qiddiya projects. The high percentage of positive sentiment also reflects hope and optimism for the future promised by the Vision, especially regarding job creation, women’s empowerment, and improvements to infrastructure and services. Vision 2030 is built upon three main pillars: A vibrant society, A thriving economy, And an ambitious nation. These pillars are interconnected and aligned to achieve national goals. The Vision Realization Programs (VRPs) serve as the driving force behind the implementation of Vision 2030, translating strategic objectives into tangible outcomes. Each program acts as a detailed roadmap, tailored through approved execution plans, guided by predefined goals and Key Performance Indicators (KPIs) over a five-year timeline. As Vision 2030 has evolved, some realization programs have been restructured to meet changing needs, reflect the kingdom’s ambitions and capabilities, and ensure full realization of the Vision. Key goals include reducing unemployment from 11.6–7%, increasing non-oil exports to 50% of non-oil GDP (up from 16%), and boosting local production from 40% to approximately 65%, in collaboration with the private sector. Meanwhile, neutral sentiment, which made up 37% of tweets, reflects balanced or observational perspectives, where users provided commentary or assessments of Vision 2030 without clear bias. These tweets often contain informational content or updates about projects without strong personal opinions. Table (6) Sentiment orientation of tweets about Saudi Vision 2030 during the study period Year Sentiments 2016 2017 2018 2019 2020 2021 2022 Total F % F % F % F % F % F % F % Positive 48659 52.73 6207 49.62 6363 50.47 7014 54.17 8322 54.15 19700 45.22 17257 47.41 113522 Negative 14357 15.56 1641 13.12 1658 13.15 1682 12.99 2125 13.83 3823 8.78 3182 8.74 28468 Neutral 29256 31.71 4662 37.27 4587 36.38 4251 32.83 4921 32.02 20042 46 15964 43.85 83683 Tota 92272 12510 12608 12947 15368 43565 36403 225673 Table (6) reveals the sentiment trends of tweets under the two hashtags related to Saudi Vision 2030 over the seven-year study period. The data shows that positive sentiments ranked first, with 113,522 occurrences, representing 50.3% of the overall tweet sentiments. Neutral sentiments came in second, with 83,683 occurrences (accounting for 37%), while negative sentiments ranked last, with 28,468 occurrences (representing 12.6%). These results indicate that the predominant sentiment among Twitter users toward Vision 2030 is positive, reflecting a widespread sense of approval among the Saudi public. This is largely due to the bold and comprehensive economic and social programs that Vision 2030 encompasses. These various programs aim to create a qualitative transformation in the cultural, social, and economic life of the Kingdom, positioning sustainable development as both the launching point and the ultimate goal in the Kingdom's journey toward joining the ranks of advanced nations. Recognizing that human capital is the foundation and central focus of all development efforts, Vision 2030 emphasizes that the true wealth of the nation lies in its people, rooted in their Arab and Islamic identity and their noble values. Figure (2) Sentiment trends of tweets about Saudi Vision 2030 during the study period Figure (2) reveals the sentiment trends of tweets under the Saudi Vision 2030 hashtags during the study period. The data clearly shows the dominance of positive sentiment over other sentiment categories throughout the years of analysis. Since the launch of Vision 2030, all state institutions have been required to unite efforts to realize its goals by reviewing their plans and programs in alignment with the Vision’s strategic objectives. This strong institutional commitment, reflected in the data, demonstrates the Saudi society’s engagement and interest in the Vision and its diverse programs. Moreover, the prevalence of positive sentiment highlights public support for the achievements of Vision 2030 across various domains—economic, social, cultural, political, and beyond—reinforcing the Vision’s role as a comprehensive roadmap for sustainable development in the Kingdom. Figure (3) Network analysis of Saudi Vision 2030 hashtags in 2016 It is clear from the network graph (3) that sentiments and public attitudes toward the most frequently used hashtags accompanying "رؤية_السعودية_2030" in 2016 were almost entirely positive, as also shown by the results of Table (5). This is reflected in the green lines that indicate a positive trend toward the programs of Saudi Vision 2030. The graph also reveals the notable density and thickness of the nodes between the main hashtag, "رؤية_السعودية_2030", at the center of the graph, and the hashtags (محمد_بن_سلمان), (التحول الوطني), (saudivision2030), and (السعودية). In social media network analysis, the nodes and the thickness of their connecting lines show the associations and strength of relationships between different hashtags. In this case, the graph shows how these hashtags are closely linked to discussions around "رؤية المملكة 2030" as the main hashtag. Figure (4) Network analysis of the Saudi Vision hashtags in 2017 The network graph (4) reveals that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag "رؤية_السعودية_2030" in 2017 were mostly positive, as also shown by the results of Table (6). This is reflected in the green lines that indicate a positive trend toward the programs of Saudi Vision 2030. We also observe the density and proximity of the nodes between the main hashtag "رؤية_السعودية_2030" at the center of the graph and the English version of the hashtag "saudivision2030", as well as hashtags like "رؤية 2030", "السعودية", and "التحول الوطني", indicating a strong overlap and frequent use of accompanying hashtags by users on the (X) platform. This also applies to other hashtags associated with the main hashtag, such as: (ولي العهد", "ريادة", "التحول الوطني", "مشروع نيوم", "مشروع البحر الاحمر", "الاخبارية", "التعليم", and "سياحة" ) with varying levels of intensity. The emergence of projects like NEOM, the Red Sea Project, tourism, and entrepreneurship marked success and coincided with the launch of Saudi Vision 2030 on April 25, 2016. Figure (5) Network analysis of Saudi Vision hashtags in 2018 The network graph (5) illustrates the network analysis of the Saudi Vision hashtags in 2018, showing that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag "رؤية_السعودية_2030" in 2018 were characterized by positivity, as also demonstrated by the results of Table (7). This is reflected in the green lines and network nodes that indicate the prevailing positive orientation toward the programs of Saudi Vision 2030. The graph also shows the density and closeness of nodes between the hashtag "رؤية_السعودية_2030" at the center and hashtags such as "السعودية", "ولي العهد", "محمد بن سلمان", "الرياض", "علاقة الجامعة بالمجتمع", "جامعة الجوف", and "اليوم الوطني", indicating alignment and integration in the use of accompanying hashtags by users on the (X) platform. This also applies to other hashtags that have secondary connections with the main hashtag, such as: "برنامج جودة الحياة", "التحول الرقمي", "ksa", "saudivision2030", "saudiarabia", "التأمين", "أتمنى", and "مجلة عين المملكة", with varying degrees of intensity. The emergence of projects like NEOM, the Red Sea Project, tourism, and entrepreneurship marked success that coincided with the early launch of Saudi Vision 2030 on April 25, 2016. Figure (6) Network analysis of the Saudi Vision hashtags in 2019 The network graph (6) illustrates the network analysis of the Saudi Vision hashtags in 2019. The data reveals that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag "رؤية_السعودية_2030" in 2019 were positive, as also demonstrated by the results of Table (9). This is reflected in the green lines, whether in the main nodes or the sub-nodes, which indicate unified positive sentiments toward the programs of Saudi Vision 2030. The graph also shows the density and closeness of the nodes between the hashtag "رؤية_السعودية_2030", which is at the center, and the hashtags (السعودية), (علاقة الجامعة بالمجتمع), (جامعة الجوف), (ولي العهد), and (محمد بن سلمان), indicating a strong alignment and frequent use of the accompanying hashtags by users on the (X) platform along with "رؤية_السعودية_2030". This also applies to other sub-hashtags connected to the main hashtag, such as: (برنامج جودة الحياة), (التحول الرقمي), (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), and (السعودية), with varying densities and node sizes. These hashtags represent the names of programs or topics related to the initiatives taken under Saudi Vision 2030. Figure (7) Network analysis of Saudi Vision hashtags in 2020 The network graph (7) reveals the network analysis of the Saudi Vision hashtags in 2020. The main and sub-nodes in the figure show that the attitudes of Twitter users were aligned with the main hashtag of the study, "رؤية_السعودية_2030", reflecting positive sentiments toward the content of these hashtags. A closer look at the data in Figure (7) shows that there are major nodes represented by green lines for hashtags that align with the content and direction of the main hashtag "رؤية_السعودية_2030", such as: (السعودية العظمى), (السعودية), (علاقة الجامعة بالمجتمع), (ولي العهد), and (محمد بن سلمان), with varying densities and node sizes. The figure also reflects the density and closeness of nodes between the central main hashtags and the peripheral hashtags such as (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), (السعودية), and (برنامج جودة الحياة). This indicates the alignment and intensity of accompanying hashtag usage by users on the (X) platform alongside the hashtag "رؤية_السعودية_2030", with varying densities and connections. These hashtags represent names of programs or topics related to those programs included in Saudi Vision 2030. Figure (8) Network analysis of the Saudi Vision hashtags in 2021 The network graph (8) reveals the network analysis of the Saudi Vision hashtags in 2021. The main and sub-nodes in the graph show that the attitudes of Twitter users were aligned with the main hashtag "رؤية_السعودية_2030” and were predominantly positive toward the content of these hashtags. A closer look at the data in Figure (8) shows that there are major and minor nodes represented by green lines for hashtags that align with the content and direction of the hashtag "رؤية_السعودية_2030", such as: (السعودية), (السعودية العظمى), (خادم الحرمين), (ولي العهد), (رؤية 2030 واقع يتحقق), (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), (السعودية), and (برنامج جودة الحياة), with varying densities and node strengths. This indicates a strong alignment and intensity in the use of accompanying hashtags by users on the (X) platform along with the hashtag "رؤية_السعودية_2030", across different densities and connections. Figure (9) Network analysis of the Saudi Vision hashtags in 2022 The data in Figure (9) presents the network analysis of the Saudi Vision hashtags in 2022. The network diagram reveals that the main and sub-nodes indicate that the attitudes of Twitter users aligned with the main hashtag "رؤية_السعودية_2030", with most sentiment directions characterized by positivity toward the content of these hashtags. A closer look at the data in Figure (9) shows that most of the main and sub-nodes appeared as green lines representing hashtags that align with the content and direction of the main study hashtag, such as: (مجلس الوزراء), (برنامج جودة الحياة), (الرياض), (برنامج التحول الوطني), (اليوم الوطني السعودي), (محمد_بن_سلمان), (saudivision2030), (saudiarabia), (ولي العهد), (الرياض), (السعودية), and (جودة الحياة), with varying node densities and strengths. This indicates a strong alignment and high frequency of use of accompanying hashtags by users on the (X) platform along with the hashtag "رؤية_السعودية_2030". Additionally, the table reveals one negative sentiment connection between the hashtag "رؤية_السعودية_2030" and the hashtag "صحيفة_واصل", as highlighted by a red line in the node connecting the two hashtags. This, similar to the 2021 analysis, may suggest some criticism raised by the newspaper regarding delays in implementing certain projects related to the Saudi Vision 2030 programs. 5.2 Discussion and Conclusion: The importance of this study emerges from the importance of the topic itself: analyzing social networks and identifying solutions and future perspectives to help evaluate the sustainability of Saudi Vision 2030. This study also helps in gaining insights that contribute to improving and accelerating the Vision’s goals. It showed that the use of modern tools and algorithms, including artificial intelligence for big data analysis, contributes to the development of research in new media and social networks. In addition to its scientific contribution in employing advanced algorithms for descriptive analysis, network analysis, and sentiment analysis, this study contributes to drawing the attention of researchers and specialists in the fields of new media and social networks toward conducting similar studies. In what follows discussion of the findings of the current study: Table (1) shows that the highest number of tweets appeared in 2016, the year Saudi Vision 2030 was launched, with (92,272) tweets. This increase is probably attributed to the intensive media campaigns that accompanied the launch of the Vision in its first year, and the resulting interactions and participation from the user audience. As shown in the table, the highest number of likes on Vision 2030 programs was in 2022, with (445,147) likes, indicating positive results and achievements realized after 7 years. The highest number of replies to tweets was in 2022, suggesting a more mature public understanding of the Vision’s programs and goals. In contrast, the most retweets, (651,470), were recorded in 2016, indicating the Saudi public’s immediate engagement with the Vision and its programs. Hashtag interaction was also prominent and clear in the launch year with 1,044,086 interactions. Table (5) reveals the dominance of positive sentiment toward the programs of Vision 2030, indicating the Saudi society's strong acceptance of the Vision’s programs and the accompanying transformations across various economic, social, and cultural levels, ultimately leading toward sustainable development. Figures (3–4) show the strong correlations between highly significant hashtags such as: "السعودية", "التحول الوطني", and "محمد بن سلمان" as sub-hashtags within the programs of Vision 2030. This can be explained by several factors: Direct relationship with the Vision : Crown Prince Mohammed bin Salman is considered the driving force behind Saudi Vision 2030. Therefore, there is a natural and strong association between the hashtag "رؤية المملكة 2030" and "محمد بن سلمان", as his name is frequently mentioned in discussions about the Vision and its initiatives. National development initiative : Vision 2030 is a national initiative aimed at developing and enhancing various sectors in Saudi Arabia. As such, the hashtag "السعودية" is closely linked to "رؤية المملكة 2030" in the context of discussions around national development and progress. "National Transformation Program" (NTP) : This is a fundamental component of Vision 2030, aiming to achieve the Vision’s goals through a variety of reforms across government, economy, and society. Therefore, the hashtag "التحول الوطني" is directly connected to the hashtag "رؤية المملكة 2030". Shared events and initiatives : New initiatives and programs are often launched under the umbrella of Vision 2030, and these frequently include references to the Crown Prince or other subprograms such as "التحول الوطني". This leads to joint engagement with these hashtags, further strengthening their connection in network analysis. Focus of official and media discourse : The official and media discourse in Saudi Arabia tends to employ certain hashtags to reinforce specific messages. When discussing Vision 2030, it is commonly linked to leadership figures such as (محمد بن سلمان) and to key initiatives like (التحول الوطني), which reinforces their connection. Table (3) highlights the prominence of images, mentions, and hashtags in the multimedia content of tweets related to Saudi Vision 2030. This can be interpreted as follows: Attracting attention : Images usually attract more attention than plain text. Users tend to engage more with tweets that contain images or visual media. Therefore, the use of images could be an effective strategy to draw more attention to tweets related to the Vision. Engagement and reach : Hashtags are typically used to organize content, while mentions are employed to increase the reach of tweets. When hashtags and mentions associated with Saudi Vision are used, tweets can reach larger segments of users interested in the topic, increasing the chances of interaction and sharing. Shift toward digital marketing : With the evolution of social media, governments and institutions have come to recognize the importance of digital marketing for reaching audiences. Using images, hashtags, and mentions is part of effective communication strategies on these platforms. Table (4) reveals the predominant use of the Arabic language in the hashtags and tweets about the Vision 2030 compared to English. This is due to the following: Target audience : The primary target audience of Vision 2030 is the citizens and residents of Saudi Arabia, who mainly speak Arabic. Since it is a national initiative aiming for comprehensive development within the Kingdom, Arabic is naturally the main language used. Cultural identity reinforcement : Using Arabic reflects the national and cultural identity of Saudi Arabia. The Vision aims to strengthen the Kingdom’s cultural and social identity, making the use of Arabic in hashtags an effective tool to support this goal. Clarity and interaction : Most Twitter users in Saudi Arabia speak Arabic. Using Arabic in hashtags makes the content clearer and easier to understand for local users, resulting in higher engagement. Direct communication with citizens : Government initiatives often use Arabic to communicate with citizens to ensure messages and policies are delivered clearly and directly. Local outreach : Arabic-language hashtags allow tweets to reach users across the Arab world, increasing their visibility both locally and regionally. Study Recommendations : The study recommends using Large Language Models (LLMs) to analyze big data in social networks instead of classification models, as LLMs have higher capabilities in interpreting texts and words. The study recommends conducting research that involves large-scale data using artificial intelligence algorithms and developing new research methods and tools for digital media analysis. The study calls on researchers and those interested in AI technologies to explore, standardize, and use modern techniques in the media field. Integrating these methods can lead to more accurate and comprehensive results. The study recommends using the Knowledge Graph application for representing and extracting information from textual data. This application provides a clearer and more accurate representation of network relationships. Future Research Directions : Future research can expand its focus by using the methodology applied in this study to qualitative data analysis, including short blogs. It is not necessarily required to follow this methodology exactly; it can be adapted by updating AI models for sentiment analysis and topic modeling, and even by modifying parts of it. This research helps clarify the methodology of social network analysis, from data collection to analysis and presentation, highlighting the need for further studies and research. Declarations The funding statements: This work was supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU) (grant number IMSIU-DDRSP2502) Conflicts of Interest: The author declares no conflicts of interest. Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. Author Contribution ContributionsMohammad Ali Alquaary wrote the main manuscript tex, Alquaary prepared figures and tables. author reviewed the manuscript. References Al-Areeshi J, Saleh F (2020) The use of big data and artificial intelligence in confronting the emerging coronavirus pandemic. Arab J Secur Stud 36(2):249–264. https://doi.org/10.26735/GYCX5740 Al-Khalifi T (2019) Social media data mining and its uses in media research: Sentiment analysis as a model. J Media Res Stud 8(8):1–73. https://doi.org/10.21608/mjsm.2019.109622 Al-Qahtani LA, Al-Mutairi SM, Al-Juhani AS (2024) The role of Saudi digital media in raising citizen awareness of cybercrime techniques in the Kingdom of Saudi Arabia. J Arts Literature Humanit Social Sci 104:283–327. https://doi.org/10.33193/JALHSS.104.2024.1085 Al-Shaddi TA (2010) Social network analysis methodology. King Saud Univ Journal: Arts 22(2):373–403. https://search.mandumah.com/Record/478946 Al-Thaqafi IM (2020) Journalistic coverage of G20 issues in light of Saudi Vision 2030. Egypt J Media Res 76:1–46. https://doi.org/10.21608/ejsc.2021.194421 Al-Toukhi MM (2018) The dependence of Saudi university students on electronic newspapers for Saudi Vision 2030: A case study. Sci J Journalism Res 15:273–334. https://doi.org/10.21608/sjsj.2018.155194 Al-Zahrani AA, Salem DF (2018) The role of social media in the formation of Saudi youth attitudes towards the Kingdom's 2030 vision. Egypt J Media Res 2018(65):193–279. https://doi.org/10.21608/ejsc.2018.86777 Ali AKA (2018) Big data and its analytics: Concept, characteristics, and applications. J Fac Arts 49(2):445–476. https://doi.org/10.21608/bfa.2018.188153 Alkathiri ES (2020) The relationship between Saudi citizen perceptions of Vision 2030 and Saudi government social media use to promote Vision 2030 [Doctoral dissertation, University of North Dakota]. UND Scholarly Commons. https://commons.und.edu/theses/3364 Alsaaidi HZ (2020) Nation branding and the case of Saudi Vision 2030 and the use of Twitter [Master's thesis, Rochester Institute of Technology]. RIT Digital Media Library. https://repository.rit.edu/theses/10615 Amato G, Behrmann M, Bimbot F, Caramiaux B, Falchi F, Garcia A, Geurts J, Gibert J, Gravier G, Holken H, Koenitz H, Lefebvre S, Liutkus A, Lotte F, Perkis A, Redondo R, Turrin E, Vieville T, Vincent E (2019) AI in the media and creative industries [White paper]. arXiv. https://doi.org/10.48550/arXiv.1905.04175 Azzalini A, Scarpa B (2012) Data Analysis and Data Mining: an Introduction. OUP USA Badran MH (2019) The impact of Big Data analytics on the efficiency of marketing campaign [Master's thesis, Syrian Virtual University] Barbieri F, Anke LE, Camacho-Collados J, Kar S, Segura-Bedmar I, Kann K, Nakov P (2022) XLM-T: Multilingual language models in Twitter for sentiment analysis and beyond. arXiv preprint. https://doi.org/10.48550/arXiv.2104.12250 Barbieri F, Camacho-Collados J, Anke E, L., Neves L (2020) TweetEval: Unified benchmark and comparative evaluation for tweet classification. In Findings of the Association for Computational Linguistics: EMNLP 2020 (1644–1650). Association for Computational Linguistics. https://aclanthology.org/2020.findings-emnlp.148 Cheng G (2018) Artificial intelligence in media industries: Creating better user experiences and maintaining high customer loyalties [Master's thesis, Drexel University]. Drexel Digital Repository. https://doi.org/10.17918/D87077 El-Sayed H (2021) Employing artificial intelligence applications to analyze social media users' sentiments in real-time during the COVID-19 crisis. Egypt J Public Opin Res 20(2):149–202. 10.21608/joa.2021.190747 Elshereef SAMA (2022) Sentiment analysis for Twitter during U.S. Presidential Election2020 Using the big data framework. Egypt J Public Opin Res 21(2):1–49. https://doi.org/10.21608/joa.2022.250344 Faraj A (2022) Investing big data to develop search and retrieval mechanisms and customize information institution services: A prospective study. Sci J Libr Documents Inform 4(11):7–42. https://doi.org/10.21608/jslmf.2021.53697.1058 Harfoush I, Al- Warqali S, Ba'di W (2019) The impact of robot anchors on the journalism profession: A semiological analytical study on a sample of news bulletins [Master's thesis, University of Ouargla]. DSpace Repository. http://dspace.univ-ouargla.dz/jspui/handle/123456789/21387 Ibrahim HG (2022) A prospective vision for adopting artificial intelligence technologies in Palestinian satellite channels. Algerian J Communication 24(1):8–29. https://asjp.cerist.dz/en/article/189698 Inoue G, Alhafni B, Baimukan N, Almatham R et al (2021) The interplay of variant, size, and task type in Arabic pretrained language models. In Proceedings of the Sixth Arabic Natural Language Processing Workshop (WANLP 2021). Association for Computational Linguistics. https://arxiv.org/abs/2103.06678 Johnson TJ, Kaye BK (2015) Site effects: How reliance on social media influences confidence in the government and news media. Social Sci Comput Rev 33(2):127–144. https://doi.org/10.1177/0894439314537029 Kumar S, Morstatter F, Liu H (2014) Twitter Data Analytics. Springer, New York, NY Kümpel AS (2020) The Matthew Effect in social media news use: Assessing inequalities in news exposure and news engagement on social network sites (SNS). Journalism 21(8):1083–1098. https://doi.org/10.1177/1464884920915374 Mansour RAMA, Abdelrazek HMS (2017) The future of data journalism in Egypt during the next two decades 2017–2037. J Mass Communication Res 120–137. https://doi.org/10.21608/JKOM.2020.108647 Md Suhaimin MS, Ahmad Hijazi MH, Moung EG, Nohuddin PNE, Chua S, Coenen F (2023) Social media sentiment analysis and opinion mining in public security: Taxonomy, trend analysis, issues and future directions. J King Saud Univ - Comput Inform Sci 35(9):833–838. https://doi.org/10.1016/j.jksuci.2023.101776 Naskar D, Mokaddem S, Rebollo M, Onaindia E (2016) Sentiment analysis in social networks through topic modeling. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16) . 46–53. European Language Resources Association. https://aclanthology.org/L16-1008 Sanousi T (2021) Theories of new media. Arab Agency for Public Relations Sawani FM (2016) Scientific research, 1st edn. Ibn Al-Nadim Publishing Sharda R, Delen D, Turban E (2021) Analytics, data science, & artificial intelligence: Systems for decision support. Pearson Education Limited Statistics (2016) Social networking Garton Timmy. Grophlcsms. http://www.Grophlcsms,com/blog/877-social-networking statisties–2010/ht Thabet S, Thabet A (2022) J Financial Commercial Res 23(1):1–40. https://doi.org/10.21608/jsst.2021.102896.1340 . The impact of big data analytics on operational efficiency of banks using data envelopment analysis: Applied to Commercial International Bank Tosun LP (2012) Motives for Facebook use and expressing true self on the Internet. Comput Hum Behav 28(4):1510–1517. https://doi.org/10.1016/j.chb.2012.03.018 Zeki WR (2015) Theory of social networks: From ideology to methodology. The Arab Forum for Social and Human Sciences. https://socio.yoo7.com/t3886-topic Additional Declarations No competing interests reported. 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-7482610","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":530242463,"identity":"e46ca2fc-3007-48ac-b720-ab77b5e3eac1","order_by":0,"name":"Mohammad Ali","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYHACxgMQmvkAlMFgQFAPVCVbAslaeOAq8WvRbT/84MDbNjt58xk5Hw/dqNmW2MDevE2C4Y8dTi1mZ9IMDs5tSzaccyN3w+GcY7cTG3iOlUkwtiXj1nIgweAwbxsz4wwJkBY2oBaJHDMJxgZm3FrOP/8A1FJvP0Mi58HhnH9ALfJvzIAOq8et5UYOyJbDiUAtDIdz20C28AC1sB3Go+VNwcE5544nz+B5ZnA4t++2cRtPWrFFYttxPA5L3/jgTVm17Qz25Mefc77dlu1nP7zxxoc/1Ti1gAEPiBBIgHDYQEQCfg1QLfwHCCkbBaNgFIyCkQoArXdfFIKB8FAAAAAASUVORK5CYII=","orcid":"","institution":"Imam Mohammad Ibn Saud Islamic University (IMSIU)","correspondingAuthor":true,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Ali","suffix":""}],"badges":[],"createdAt":"2025-08-28 17:53:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7482610/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7482610/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93708823,"identity":"a3cd1fda-05f5-4b39-a0ae-9579be156729","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4024495,"visible":true,"origin":"","legend":"","description":"","filename":"artticle.docx","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/7714a8c6f584b33152562f29.docx"},{"id":93708816,"identity":"f3c6c4df-3c86-48ae-8372-ff4a10f44bef","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3976,"visible":true,"origin":"","legend":"","description":"","filename":"9129d7ab567246ce994bee9e5400aa67.json","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/4e80409ba06c001c17dae9d4.json"},{"id":93708819,"identity":"61a55a22-553e-4bad-80df-9b930028cd68","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":157271,"visible":true,"origin":"","legend":"","description":"","filename":"9129d7ab567246ce994bee9e5400aa671enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/0c389a103155fe81fb508c51.xml"},{"id":93708821,"identity":"91813d30-4c0e-48f1-ba24-86058768fec8","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":318186,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/6e29ca68d1a69c2fd3984c6d.jpeg"},{"id":93709631,"identity":"15acccf1-c17b-49cc-818c-0f94b9619552","added_by":"auto","created_at":"2025-10-16 17:33:53","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89849,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/9594130a44ff352844e9a547.png"},{"id":93709452,"identity":"b1368adb-30b7-481f-9ffc-9f7910859fd5","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":662690,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/c9fe0685a940903712762952.png"},{"id":93709454,"identity":"bc6b2eb5-61d3-4e9d-8865-ff9dceb64563","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":483197,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/da1e8608291800b5a19a77bb.png"},{"id":93708837,"identity":"7665f031-c294-4de8-965f-275c5adbe11f","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":730422,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/174af1e1cadc7f82711b1583.jpeg"},{"id":93709456,"identity":"28324f04-ba73-4457-8229-87280c60dce2","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":474914,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/dc6c627cd137b85f795e14a7.png"},{"id":93708838,"identity":"29affa25-cf69-4739-9834-091d4643fdbf","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":638184,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/ebc637c9620252cd20d609eb.png"},{"id":93709632,"identity":"96bf4150-2f9f-4dcf-90d1-5757da4598a7","added_by":"auto","created_at":"2025-10-16 17:33:53","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":530255,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/7f75507e51d142dcbc7e8232.png"},{"id":93709459,"identity":"6e31ca87-32b8-4fef-9ffc-41ec13e47c5e","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":473013,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/b5ceb4eb77d6f022cc549f2a.png"},{"id":93708827,"identity":"50a100b3-db13-4adc-b9bd-d6f6d1b7da6f","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81633,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/06bbe043e8be5a0ea1bc9632.png"},{"id":93708831,"identity":"b5253a2b-af2c-4e89-b383-d432ee237fe3","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20079,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/9917e02b75337f961d007f23.png"},{"id":93708841,"identity":"e4ecc4e4-74d8-4564-95ed-e9d031ca6dbc","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":170116,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/a112763af4726cf47f6c5562.png"},{"id":93708840,"identity":"d6aa9c28-2d76-49a0-a9c9-544a344c2f89","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127012,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/a837a828f222ee3fbf7312bf.png"},{"id":93709460,"identity":"a5e1e8bc-6e74-4473-b3c5-23f9474862af","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":261322,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/2973340da90cec48b89f4f47.png"},{"id":93710085,"identity":"b9dc4319-5d5f-4ca0-ab0d-747eee7123c5","added_by":"auto","created_at":"2025-10-16 17:41:53","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124390,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/c3a48db85c93a496bd3390f9.png"},{"id":93708843,"identity":"eb8c5fd0-d28b-434d-8bc1-c98d641d0237","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162347,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/2b259657cc5f4f4f3b4da978.png"},{"id":93709461,"identity":"8be3d5f6-8b57-4205-9b81-2c95b33d2256","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138068,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/b8a9d707fc712ab314e3e131.png"},{"id":93708844,"identity":"f9da780d-60e9-4b82-aba2-35b0852179f0","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122963,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/100ddbd1905e240b674efd5e.png"},{"id":93708839,"identity":"89ffb914-b23a-4111-82ea-437fe5f29587","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155833,"visible":true,"origin":"","legend":"","description":"","filename":"9129d7ab567246ce994bee9e5400aa671structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/4e4d043b38d77904a112044d.xml"},{"id":93708846,"identity":"0fbb46e4-f81d-4b12-a599-27e99323241f","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"html","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162080,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/ee33d1c8735b4d7f1f7a1e45.html"},{"id":93708815,"identity":"4543c95b-fcb3-4c60-8aa7-6c0f2ad3f170","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":116815,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eMethodological Procedures Used in the Study\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/380e014ca08b2e0e91566633.jpeg"},{"id":93709447,"identity":"1f246b4e-6d42-4bb1-bb6d-bc49ca0b4ae2","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":246012,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSentiment trends of tweets about Saudi Vision 2030 during the study period\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/f014e2fa4d01692f6c395365.png"},{"id":93708824,"identity":"ae84876d-7b89-4bbf-9541-208adf889c1f","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":639162,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of Saudi Vision 2030 hashtags in 2016\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/711997e4b91b3d6eaeb8e57f.png"},{"id":93709450,"identity":"a63e39d2-1e20-4171-92b4-c29c2d7c6209","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":561986,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of the Saudi Vision hashtags in 2017\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/687cc43b2aadc3c845c71e0d.png"},{"id":93709629,"identity":"46f31206-4022-4db2-bafc-8ec1b9252ac1","added_by":"auto","created_at":"2025-10-16 17:33:53","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":491927,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of Saudi Vision hashtags in 2018\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/450a3f0003a2f2db829aa363.png"},{"id":93709449,"identity":"ed545711-60cb-4021-99ff-74187d3ee032","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":573740,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of the Saudi Vision hashtags in 2019\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/68f4dc9b07e33b598856fc95.png"},{"id":93709451,"identity":"e4dab5cf-03e4-4c35-8a6c-276bfa04e7a8","added_by":"auto","created_at":"2025-10-16 17:25:53","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":599459,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of Saudi Vision hashtags in 2020\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image7.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/4945d5e3e6b6fc1170798e5b.png"},{"id":93708829,"identity":"1b9db8af-0b45-4927-bdf6-6c212fc982a3","added_by":"auto","created_at":"2025-10-16 17:17:53","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":560116,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of the Saudi Vision hashtags in 2021\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image8.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/0aba2219cb018585d4196ea6.png"},{"id":93709630,"identity":"60025c4b-0e9e-420e-9bd2-48c96d722b0d","added_by":"auto","created_at":"2025-10-16 17:33:53","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":542555,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eNetwork analysis of the Saudi Vision hashtags in 2022\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image9.png","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/a7c1b58eaa4e01f3d9eaec5a.png"},{"id":95282459,"identity":"f3de79c6-dde6-455e-87de-a71d04e72f8b","added_by":"auto","created_at":"2025-11-06 09:24:08","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6232889,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7482610/v1/8c76e463-e833-40b3-b797-81f4f493cb60.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Employing Network Analysis of Big Data on Platform (X) in Relation to Saudi Vision 2030 (An Analytical Longitudinal Study for the Period from 2016–2022)","fulltext":[{"header":"1- Introduction","content":"\u003cp\u003eIn recent years, there has been growing interest in social networks and virtual communities, especially as the Internet has become the ideal platform for forming such communities and reaching millions of people in remarkable ways.\u003c/p\u003e\u003cp\u003eThe Internet and its interactive features have become an essential part of daily life for individuals and groups. The term \"virtual community\", once a subject of scholarly attention, has now become a widespread and commonly understood concept\u0026mdash;not only in academic studies but also among Internet users in general (Zaki, 2015). With the evolution and expansion of virtual communities, new theories and concepts have emerged that re-evaluate many ideas related to media and communication. Additionally, the significant progress in the use of social networks has contributed to shaping theoretical frameworks and research methodologies related to these platforms (Sanousi, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eAs a result of the rapid advancements in online communication, social media platforms now offer users highly interactive environments that transcend geographical boundaries, attracting the time and attention of young people in particular, and all age groups in general. These platforms allow individuals to share personal experiences and engage in rich social interaction, integrating personal, interpersonal, group, and public communication into a unified environment that is reshaping their social and communicative structures (Tosun, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2012\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThis virtual interaction can be observed in public discourse on Saudi Vision 2030, a strategic framework for national development, as seen in discussions on the platform X using the hashtags \u0026ldquo;#SaudiVision2030\u0026rdquo; and \u0026ldquo;#رؤية_السعودية_2030\u0026rdquo;. This study covers the period from the initial use of these hashtags on April 21, 2016, through the end of 2022, capturing a range of public perspectives. The official announcement of Vision 2030 was made through the \u0026ldquo;SaudiVision2030\u0026rdquo; account on April 25, 2016.\u003c/p\u003e\u003cp\u003eThis study aims to bridge the gap between public perception and the broader context of sustainability. By interpreting sentiments and prevailing themes in discussions on Platform X, it seeks to contribute to a deeper understanding of how Vision 2030 is viewed in relation to global sustainability efforts and its potential impact on achieving various Sustainable Development Goals (SDGs).\u003c/p\u003e\u003cp\u003eThe conversations reflected in these tweets provide a unique insight into public mindset, revealing how different aspects of Vision 2030 are perceived locally. Analyzing this discourse offers valuable insights into collective sentiment toward the Vision\u0026rsquo;s sustainability initiatives\u0026mdash;particularly relevant given the alignment between Vision 2030\u0026rsquo;s objectives and the SDGs, such as expanding renewable energy, encouraging economic diversification, and enhancing social well-being. The sentiments and topics expressed by X platform users reflect not only immediate responses to these initiatives but also offer a forward-looking perspective on the area\u0026rsquo;s most likely to gain public support.\u003c/p\u003e\u003cp\u003eUnderstanding this digital discourse is vital for assessing the sustainability of Vision 2030. It helps identify areas where public awareness or engagement may need to be strengthened, and where communication strategies might require adjustment to better align with public expectations. Thus, the study moves beyond basic sentiment analysis to develop a deeper understanding of how the narrative surrounding sustainable development within Vision 2030 is being shaped through social dialogue, ultimately influencing public opinion and potentially the trajectory of achieving the SDGs.\u003c/p\u003e\u003cp\u003eDrawing upon the scholarly theories, prior research, and the interdisciplinary methodology of Social Network Analysis (SNA)\u0026mdash;which reveals the structure of relationships among social entities and how these structures impact other social phenomena\u0026mdash;the study investigates the patterns of interaction among actors (tweeters). SNA is a robust framework to analyze social behavior, online communication within groups, and networked relationships across social networks. This study, therefore, applies network analysis techniques to big data from the Platform X regarding Saudi Vision 2030. The analysis is conducted as a longitudinal study from 2016 to 2022.\u003c/p\u003e"},{"header":"2. Literature Review","content":"\u003cp\u003eA review of prior research indicated into three main categories.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Studies Addressing Artificial Intelligence Technologies\u003c/h2\u003e\u003cp\u003ePrevious studies have focused on the scholarly legacy concerning the application of artificial intelligence (AI) technologies in media and social networks, particularly in network analysis, while also exploring the role of social media platforms in supporting the goals of Saudi Vision 2030. Given their widespread influence and reach, social media platforms have gradually shaped individuals\u0026rsquo; perceptions by serving as trusted sources of data. Social media, especially microblogging sites such as \u003cem\u003ePlatform X\u003c/em\u003e, have a significant influence on public opinion, functioning as influential information sources even for those not actively seeking news, who may come across it through friends\u0026rsquo; activities or casual discussions (Johnson, et al., 2015; K\u0026uuml;mpel, A. S., 2020).\u003c/p\u003e\u003cp\u003eThe growing capabilities of machine learning algorithms, particularly in natural language processing (NLP), have demonstrated efficiency in analyzing large datasets, making them essential tools for extracting insights from big data in social networks. NLP has undergone a major transformation due to the emergence of Transformer models, which marked a significant leap by enabling more accurate, large-scale understanding and processing of language.\u003c/p\u003e\u003cp\u003eThe role of social media in shaping news engagement has become more evident. Platforms like \u003cem\u003eX (formerly Twitter)\u003c/em\u003e are not only channels for disseminating news but also influential tools for enhancing user engagement and interaction. These platforms help in forming public awareness and perceptions regarding specific issues, based on how content is presented and how users engage with it\u0026mdash;highlighting the pressing need to understand how social media affects news dissemination and interaction (K\u0026uuml;mpel, A. S., 2020).\u003c/p\u003e\u003cp\u003eThe importance of topic modeling in sentiment analysis on social media is evident in a study titled \u003cem\u003e\"Sentiment Analysis in Social Networks through Topic Modeling\"\u003c/em\u003e, which applied the Latent Dirichlet Allocation (LDA) algorithm to explore topic distribution in conversations and connect them with various sentiments. This approach enables the identification of user groups or sub-communities within the network and the assessment of how affiliation affects user sentiments. It provides deeper insight into how topics and emotions interact within social networks and how sentiments and themes are distributed across them (Naskar et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Similarly, Abdulhamid (2020) confirmed the effectiveness of AI in journalistic work\u0026mdash;especially the use of bots for covering economic, sports, and weather news. Such bots can be programmed for automated conversations on websites and social media, big data processing, and machine translation. The study's results also emphasized the importance of AI in improving the structure and quality of media content.\u003c/p\u003e\u003cp\u003eCheng (\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2018\u003c/span\u003e) explored how AI techniques and algorithms could help media professionals better understand their audiences, their preferences, and their reactions to displayed content\u0026mdash;thus enabling them to provide content that meets audience satisfaction through tailored applications and multimedia interfaces. The study suggested that audiences tend to focus on news relevant to their personal lives and interests and dismiss irrelevant information.\u003c/p\u003e\u003cp\u003eAmato et al. (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2019\u003c/span\u003e) conducted a study to explore AI tools in media production, highlighting their potential to enrich the media industry, especially visual media\u0026mdash;towards greater creativity. AI enables functions such as content-based image retrieval, image annotation, and user-preference-based image searches. Such capabilities provide media professionals with diverse options for producing creative visual content.\u003c/p\u003e\u003cp\u003eHarfoush et al. (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2019\u003c/span\u003e) emphasized the role of robot journalism in influencing the media profession. It predicted that robot anchors could potentially replace human anchors in the future. Robot anchors are expected to carry semantic and implicit dimensions and contribute to enhancing the media field.\u003c/p\u003e\u003cp\u003eAl-Ezza (2017) confirmed that modern television technologies have boosted viewship for news programs, but raised concerns among media professionals about AI developments, which take two main forms: first, to the replacement of human job functions by AI systems capable of performing tasks with high efficiency, lower risk, and minimal cost; and second, the potential loss of human control as AI systems increasingly participate in decision-making .\u003c/p\u003e\u003cp\u003eRegarding future AI adoption over the next decade (2021\u0026ndash;2031). Ibrahim (\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) revealed that most respondents indicated economic factors as the most influential in adopting AI in Palestinian satellite channels. This is because technological transformation requires substantial financial resources. Professional factors such as staff training and qualification were also highlighted.\u003c/p\u003e\u003cp\u003eSimilarly, Mansour et al. (2017) in \u003cem\u003e\"The Future of Data Journalism in Egypt (2017\u0026ndash;2037)\"\u003c/em\u003e found that the main obstacle to data journalism is the lack of qualified media professionals capable of using and applying data journalism. However, the motivation behind employing data journalism lies in improving journalistic content to attract audiences and meet the evolving demands of the digital era by incorporating data into journalistic storytelling.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Studies on Sentiment Analysis and Big Data\u003c/h2\u003e\u003cp\u003eSentiment analysis, based on opinion mining and affective computing theories, has become widely used to gauge public mood and measure trends across various domains such as marketing, politics, and social media research.\u003c/p\u003e\u003cp\u003eSentiment analysis is a subfield of natural language processing (NLP) that involves identifying and classifying opinions expressed in text to determine the writer's stance toward a particular topic. This study relies on BERT models for sentiment analysis, leveraging their advanced understanding of linguistic context and details. BERT enables more accurate and context-aware analysis by processing text bidirectionally\u0026mdash;unlike traditional models that process text sequentially.\u003c/p\u003e\u003cp\u003eSeveral studies have applied sentiment analysis, such as Elshereef (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2022\u003c/span\u003e), which analyzed sentiments in tweets during the 2020 U.S. presidential elections. The study found that both candidates received similar levels of positive and negative opinions, with a sentiment classification difference of less than 1% favoring Biden\u0026mdash;who received slightly more positive sentiment than Trump. This was later confirmed by the actual election results. These findings suggest that sentiment analysis using big data from Twitter can serve as a precise and cost-effective tool for measuring public opinion toward candidates and predicting election outcomes.\u003c/p\u003e\u003cp\u003eFaraj (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) examined the utilization of big data to improve search and retrieval mechanisms and personalize services in information institutions, using a foresight-based approach. It revealed that big data management in these institutions undergoes stages of data collection, flow, storage, display, and analysis. These processes aim to enhance search capabilities and service personalization and help overcome challenges posed by content from various digital repositories. The study emphasized the potential of big data systems to offer rich search experiences and services that meet user informational needs. It employed a descriptive methodology, focusing on content analysis, and reviewed global best practices in information institutions.\u003c/p\u003e\u003cp\u003eThabet et al. (2022) explored the impact of big data analysis on the operational efficiency of banks using Data Envelopment Analysis (DEA). The results indicated that one of the main reasons for low bank efficiency was the decline in non-interest income. However, big data analysis had a positive impact on efficiency scores, confirming that the bank succeeded in adopting a suitable financial technology strategy. The study emphasized the importance of integrating internal bank data with insights derived from big data analysis.\u003c/p\u003e\u003cp\u003eEl-Sayed (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2021\u003c/span\u003e) investigated the use of AI applications for real-time sentiment analysis of social media users during the COVID-19 pandemic. The results showed that most digital citizens expressed negative sentiments toward the virus on Twitter, with fear being the dominant emotion. Using topic modeling, COVID-19-related tweets were categorized into five main themes: healthcare environment, emotional and psychological support, business economy, social change, and psychological stress. The study concluded that\u003c/p\u003e\u003cp\u003e(a) Twitter can serve as a promising entry point to reflect public awareness,\u003c/p\u003e\u003cp\u003e(b) Tweets can be used to monitor the intensity of crises over time, and\u003c/p\u003e\u003cp\u003e(c) Sentiment analysis confirms the effectiveness of geotagged tweet messages in identifying regions most affected by the crisis.\u003c/p\u003e\u003cp\u003eAl-Areeshi \u0026amp; Saleh (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2020\u003c/span\u003e) explored the use of big data and AI in COVID-19 pandemic. It concluded that deep learning techniques could process CT scan images by training models on relevant datasets, enabling rapid diagnosis and decisions regarding quarantine or medical treatment\u0026mdash;thus accelerating response measures.\u003c/p\u003e\u003cp\u003eBadran (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2019\u003c/span\u003e) investigated the impact of big data analytics on marketing campaign efficiency through a case study of Syriatel. The study concluded that the speed of data analysis via a big data platform directly influenced campaign performance. The platform allowed the analysis of millions of records and generated user features, including predicting customer churn. The company developed an integrated system covering all data lifecycle stages\u0026mdash;from collection to processing, analysis, storage, and web interfaces designed for ease of use by professionals.\u003c/p\u003e\u003cp\u003eA study by Zaki et al. (2016) introduced a sentiment analysis system for Arabic news and articles, known as \u003cem\u003eSASAN\u003c/em\u003e. It focused on opinion mining within Arabic news and articles to extract direct sentiment at the article level. Given the length of articles, the researchers proposed a novel methodology first to identify opinion sentences related to the article's main goal. They used machine learning and Typed Dependency Relations (TDR) to extract such sentences, identifying those with high-frequency nouns or adjectives as target sentences. They then built a sentiment lexicon using machine learning, based on a dataset covering fields like politics, economy, government, sports, and arts. Three methods were used for sentiment extraction: lexicon-based, machine learning-based, and opinion sentence extraction. The study concluded that the machine learning-based lexicon approach (using SVM and TDR) yielded the most effective results.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Studies Addressing Saudi Vision 2030\u003c/h2\u003e\u003cp\u003eThe Kingdom of Saudi Arabia has adopted Vision 2030, which aims to build the necessary capacities and capabilities to achieve the Kingdom\u0026rsquo;s ambitious goals by launching 13 developmental programs. These programs serve as a roadmap for economic and developmental work across all fields. The vision outlines the Kingdom\u0026rsquo;s general directions, goals, and commitments to build a vibrant society, a thriving economy, and an ambitious nation. This was highlighted in a study by Al-Thaqafi (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), which noted that the newspapers analyzed in his study showed interest in issues related to human empowerment and in shaping new horizons for Saudi society.\u003c/p\u003e\u003cp\u003eMany media and communication experts indicate that social networks are the fastest means of communication in attracting millions of members and users over recent years. These platforms emerged in the early years of this century, reflecting their ability to meet the diverse communication needs of various user groups (Statistics, \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). This was confirmed by Al-Qahtani (2019), which concluded that social media is one of the most important means of communication in Saudi society today, as it facilitates the dissemination of news from multiple sources. This aligns with Al-Zahrani \u0026amp; Salem (2019), which found that the main reasons young people rely on social media to obtain information about Vision 2030 are the ease of accessing information, followed by the ability to comment, participate, and share their views. Several outcomes have resulted from young Saudis following social media coverage of the Vision, including supporting for state\u0026rsquo;s reform measures, increasing awareness and perception, and fostering a desire to participate.\u003c/p\u003e\u003cp\u003eElectronic journalism is among the new communication means preferred by Saudi society. Al-Toukhi (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2018\u003c/span\u003e) indicated that the electronic newspapers followed the most by Saudi university students included \u003cem\u003eSabq\u003c/em\u003e, \u003cem\u003eOkaz\u003c/em\u003e, \u003cem\u003eAjil\u003c/em\u003e, \u003cem\u003eAl-Wiam\u003c/em\u003e, and \u003cem\u003eAl-Riyadh\u003c/em\u003e.\u003c/p\u003e\u003cp\u003eBen Labda\u0026rsquo;s study (2018) investigated the role of social media in shaping political awareness of Vision 2030 among the public from the perspective of Saudi experts and specialists. The study explored the sources that Saudis rely on to obtain information about the government\u0026rsquo;s future goals, the implementation stages, the competent authorities, and the future priorities for Saudi Arabia.\u003c/p\u003e\u003cp\u003eIn the same vein, Alkathiri, (\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2020\u003c/span\u003e) revealed a positive relationship between the Saudi government\u0026rsquo;s use of social media and its influence in convincing Saudi citizens of Vision 2030. The majority of survey participants agreed that the Saudi government uses new media to persuade public opinion to trust Vision 2030.\u003c/p\u003e\u003cp\u003eFurthermore, Alsaaidi (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2020\u003c/span\u003e) examined the Saudi government\u0026rsquo;s approach in using a national branding promotion strategy and presenting various values related to Vision 2030 via social media as a means of interaction with the world, specifically through platform (X). The researcher analyzed tweets related to the national brand of Vision 2030 posted on the account (2030SaudiVision). The results of 2,117 tweets revealed the Kingdom\u0026rsquo;s tendency to use platform (X) as a trusted tool for promoting Vision 2030 and enhancing its position on the world stage.\u003c/p\u003e\u003cp\u003e\u003cb\u003eKnowledge Gap\u003c/b\u003e\u003c/p\u003e\u003cp\u003eA review of previous literature shows that the social network analysis is an emerging methodology that has gained considerable attention in international academic circles, but less in the Arab world. This multidisciplinary methodology uses a range of algorithms, including artificial intelligence for qualitative content analysis and analytical algorithms for detecting relational networks, making it suitable for interdisciplinary media studies. However, higher education institutions and academic departments in Arab universities have been slow to adopt such advanced methodologies, especially in the field of digital media.\u003c/p\u003e\u003cp\u003eMost earlier studies have relied on quantitative content analysis tools to investigate digital content on various platforms, whereas this study employs social network analysis methodology to analyze big data from platform (X), formerly known as Twitter.\u003c/p\u003e\u003cp\u003eThe current study aims to expand the use of machine learning strategies, mainly sentiment analysis, which can provide significant insights into social media trends. Network analysis can offer explanations for topics instead of focusing solely on the emotional content of online conversations. Network analysis identifies topics that stimulate user interaction on platform (X) regarding Vision 2030 programs.\u003c/p\u003e\u003cp\u003eThis study will provide comprehensive and precise insights into Saudi Vision 2030 programs. This approach will significantly contribute to understanding the relationship between events and social media discourse, highlighting the power and potential of advanced machine learning techniques in the era of big data and artificial intelligence algorithms.\u003c/p\u003e\u003cp\u003eThe current research aligns with studies by Elshereef (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) and Zeki (2016) in relying on sentiment analysis tools. These studies confirm that opinion mining and sentiment analysis are more effective when based on opinion lexicons and machine learning methods, emphasizing their value in assessing the positive and negative sentiments expressed by social network users.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResearch Questions\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat are the characteristics and content of the hashtags that addressed Saudi Vision 2030 during the study period?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat are the main topics included in the tweets' hashtags related to Saudi Vision 2030 during the study period?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat sentiment trends are reflected in users\u0026rsquo; engagement with the hashtags of Saudi Vision 2030 during the study period?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat network relationships emerge from users' sentiments in the hashtags of Saudi Vision 2030 during the study period?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat network relationships emerge from the sentiments expressed through emojis in Saudi Vision 2030 hashtags during the study period?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eWhat are the methodological steps involved in conducting social network analysis in this study?\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"3. Theoretical Framework","content":"\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Network Theory\u003c/h2\u003e\u003cp\u003eMany theorists in the field of media and communication, as well as in the broader social sciences, emphasize the need for advanced research tools to study social networks. Among these tools is social network analysis- described not as a standalone theory, but rather as a methodology.\u003c/p\u003e\u003cp\u003eNetwork theory is considered a fundamental part of graph theory, which, in computer science and network sciences deals with the study of graphs as representations of information and symmetrical or asymmetrical relationships between discrete entities. The theory is referred to as the network approach, social network analysis, or network representation, all derived from computer science. It has been used in the field of new media to describe and diagnose forms of online social networking, to identify the relationships that connect citizens with new technologies, and to better understand contemporary social and cultural changes in light of the concepts of individualism and decentralization.\u003c/p\u003e\u003cp\u003eIn this study, network theory is applied to analyze and examine complex social structures with broad applications, including the use of various graph types, and advanced computational techniques through which the relational patterns of nodes\u0026mdash;representing hashtags in tweets\u0026mdash;and links, i.e., connections, are analyzed based on mathematical calculations. These calculations yield metrics for network structure or parameters that define the characteristics of network activity, social roles, and levels of participation. The primary purpose of network analysis lies in uncovering the types of connections between hashtags, identifying benefits and constraints, and understanding the overall network structure. It also focuses on network properties while taking into account that this network analysis may contribute to the construction of scenarios based on the patterns of connections and nodes across groups.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Sentiment Analysis\u003c/h2\u003e\u003cp\u003eSentiment Analysis is a branch of Natural Language Processing (NLP) that involves identifying and classifying opinions expressed in text to identify the writer\u0026rsquo;s stance toward a particular subject. The current study draws on BERT models for sentiment analysis, benefiting from its advanced understanding of language context and nuances. BERT (Bidirectional Encoder Representations from Transformers) enables more accurate and context-aware analysis by processing the text bidirectionally, unlike traditional models that read the text sequentially.\u003c/p\u003e\u003cp\u003eSentiment analysis, grounded in opinion mining and affective computing theories, is widely used to gauge general mood in diverse fields such as marketing, politics, and social media analysis. The levels of sentiment analysis, according to text output, are divided as follows. (Md Suhaimin et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eDocument-level sentiment analysis\u003c/b\u003e refers to analyzing the writer\u0026rsquo;s emotions and detecting feelings such as anger, joy, etc.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eFine-grained sentiment analysis\u003c/b\u003e refers to analyzing the resulting and reflected sentiments from the text: positive, negative, and neutral.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eAspect-based sentiment analysis\u003c/b\u003e refers to the opinions the writer focused on in a particular aspect of the document rather than others.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eLexicon-based sentiment analysis\u003c/b\u003e refers to building an opinion lexicon to understand others' intentions toward the document topic through expressive words in the text.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003cp\u003eThe stages, techniques, and tools of sentiment analysis vary. The main steps in conducting research according to sentiment analysis are as follows (Al-Khalifi, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2019\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eCollecting data from social media platforms.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003ePreparing and preprocessing data using NLP techniques.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eApplying algorithms to perform analysis and extract the opinions or sentiments within subjective texts and determine their polarity.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003ePresenting results using charts and graphs.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Study Terminologies\u003c/h2\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eSocial Network Analysis\u003c/b\u003e: A mixed method, interdisciplinary approach used to uncover the structure of relationships between social entities and examine the influence of these structures on other social phenomena. It investigates patterns of social relationships between actors (users) by mapping and measuring the connections and flows between people, groups, organizations, computers, websites, and other knowledge-processing entities. In this framework, nodes/vertices represent individuals, while edges/links represent the relationships or flows between them. In short, social network analysis provides both a visual and mathematical representation of human relationships, along with an analysis of social media content and the sentiments embedded within it.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eSentiment Analysis\u003c/b\u003e: A branch of NLP that involves identifying and classifying opinions expressed in text to determine the writer\u0026rsquo;s position toward a specific topic.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eSocial Media Analysis\u003c/b\u003e: Drawing on theories related to social networks and their influence on public opinion; social media analysis seeks to understand the dynamics of online communities and dissemination of information. On platforms such as X (formerly Twitter), real-time information sharing generates vast volumes of data that are ideal for sentiment and public discourse studies. The size and diversity of tweets make this approach particularly effective for capturing immediate reactions and tracking the evolution of narratives about major events.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Methodology","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e4.1 Type of Study\u003c/h2\u003e\u003cp\u003eThis study is classified as descriptive-explanatory research that aims to conduct a network analysis of big data from the (X) platform regarding Saudi Vision 2030. It combines traditional statistical methods to analyze data from a quantitative perspective (e.g., frequencies, numerical measures) with AI tools and algorithms to examine data from a qualitative perspective (e.g., sentiment analysis of textual data). This includes techniques such as data mining, text mining, social media mining, and opinion mining. These methods are adopted due to the fact that the primary dataset is large-scale and massive, making it difficult to extract meaningful information and insights using traditional methods (Azzalini \u0026amp; Scarpa, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2012\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThere is still no universally accepted process for scientific structural analysis, as the steps involved can vary by case and by analyst (Sharda et al., 2020). However, certain steps, such as data collection and data preprocessing, are essential in most analyses. These steps can differ and reveal the unique structure of each study (Kumar et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). Often, the source of textual data includes social media posts, comments, academic articles, blogs, and other online content.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e4.2 Study Approach\u003c/h2\u003e\u003cp\u003eThe study adopted a mixed-methods approach within the framework of integrative research to analyze the data of the applied study. This approach adds greater depth to quantitative media research and enhances the objectivity of qualitative analysis, thereby helping to overcome the methodological limitations of each (Sawan, 2016).\u003c/p\u003e\u003cp\u003eThe quantitative approach was employed in the content analysis to calculate frequencies and percentages, while the qualitative approach was used through AI algorithms to identify sentiments and underlying topics in these tweets.\u003c/p\u003e\u003cp\u003eThe study also relied on the social network analysis (SNA) approach, which provides a number of modern tools for identifying the most trending and widely discussed issues. This allows tracking discussion topics and analyzing how they evolve over time.\u003c/p\u003e\u003cp\u003eThe SNA approach enables new analytical methods that are not easily achievable through traditional methodologies that rely on research tools such as interviews and observations. It has been developed to analyze virtual social structures.\u003c/p\u003e\u003cp\u003eThe importance of SNA lies in its ability to explain the reasons behind certain behaviors of network members. Understanding these behaviors is closely linked to other factors such as individual and group relationships, as well as the culture of society under study.\u003c/p\u003e\u003cp\u003eThis approach also helps in understanding the community dynamics resulting from interactions among its members, the influence of individuals on those around them in the network, and consequently, their cumulative impact on the network as a whole (Al-Shaddi, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2010\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eStudy Population and Sample\u003c/b\u003e\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003cp\u003eThe population of the current study comprised of social media platforms. Platform (X), formerly known as Twitter, was selected from among social networking platforms for the analytical study for the following reasons:\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eIt is preferred by the Saudi society. According to a recent scientific study, 63% of the Saudi population use platform (X) daily as a source of information and for conducting searches.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eThe Kingdom of Saudi Arabia ranks first globally in terms of the percentage of active users, with 41% of internet users in the country regularly tweeting on Platform (X).\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003ePlatform (X) offers features such as retweeting, liking, replying, and displaying trendy hashtags on the user's homepage. This makes it easier for users to identify and engage with the most discussed topics. Unlike other platforms that do not display trending topics, Platform (X) enables users to see the conversation. Consequently, when a user logs into platform (X), they can easily see the issues occupying users' attention and then decide whether to participate in the discussion or simply observe.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003eThe study focused on two hashtags from the official account of Saudi Vision 2030 (SaudiVision2030), which was launched on April 25, 2016: The Arabic hashtag: \"#رؤية_السعودية_2030\", and the English hashtag: \"#saudivision2030\u003cb\u003e\".\u003c/b\u003e The study extended over a period of 7 years, from April 25, 2016, to the end of 2022. The total number of tweets collected under these two hashtags was 266,991, of which 240,644 tweets were under the Arabic hashtag and 26,347 under the English one.\u003c/p\u003e\u003cp\u003eIn total, 20 related hashtags were selected for analyzing the sentiment trends of users regarding the Vision, as shown in the study tables. Additionally, 45 hashtags were included in the network analysis conducted throughout the entire 7-year period.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e4.4 Data Collection Tools\u003c/h2\u003e\u003cp\u003eThe study relied on tools and data collection through a subscription to the API of platform X, combined with custom Python scripts developed to retrieve the data. Due to the large volume of data, the processes of collection, filtering, and analysis lasted a full year.\u003c/p\u003e\u003cp\u003eThe analysis involved gathering data while emphasizing the critical importance of obtaining highly representative user data. These data\u0026mdash;referred to as the data source in text mining\u0026mdash;were extracted from microblogs, comments, academic articles, and social media content.\u003c/p\u003e\u003cp\u003eA comprehensive dataset was collected from user tweets and their comments, along with associated features (time, likes, replies, retweets, location, etc.) for each tweet from the text-rich environment of the social media platform X. The dataset specifically included several hashtags mentioned within the tweets.\u003c/p\u003e\u003cp\u003eBig data tools were used to overcome the limitations of storage and processing of the massive, diverse data volumes in social networks. This requires an integrated set of tools and procedures for handling big data, as outlined by (Ali, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2018\u003c/span\u003e):\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eData Mining Tools\u003c/b\u003e: Manage unstructured data such as text and user activity, which are distributed across various devices on the web.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eData Analysis Tools\u003c/b\u003e: Apply methods such as comparison, classification, approximation, and correlation in order to reach the desired outcomes.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eData Visualization Tools\u003c/b\u003e: Present final analysis results in visual and graphical form, based on the study\u0026rsquo;s predefined objectives.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e4.5 Study Limitations\u003c/h2\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eTopical Scope: Limited to two hashtags from the official account of Saudi Vision 2030 (SaudiVision2030): the Arabic hashtag #رؤية_السعودية_2030, and the English \"#saudivision2030\".\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eTemporal Scope: Covered a 7-year period, from April 25, 2016, to December 30, 2022.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003eSpatial Scope: Restricted to interactions taken place on Platform (X), though the data included contributions from users worldwide.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e4.6 Statistical Methods\u003c/h2\u003e\u003cp\u003eDue to the large volume of data, a variety of traditional, modern, and AI-based tools and algorithms were combined to analyze the data both quantitatively (frequencies and numerical data) and qualitatively (sentiment analysis). The Python programming language was the primary tool for analysis.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e5.7 Methodological Procedures of the Study\u003c/h2\u003e\u003cp\u003eThe researcher followed several methodological procedures to obtain the results, including data collection and preprocessing, sentiment analysis, and then converting the results extracted from qualitative analysis into quantitative form.\u003c/p\u003e\u003cp\u003eArtificial intelligence models mentioned in the AI-related literature review were employed, specifically three sentiment analysis models, along with the parameters shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003e4.8 Steps of Data Collection and Processing\u003c/h2\u003e\u003cp\u003eIn modern data analysis, whether in data mining, text mining, or social media mining, the primary data sources are often vast, posing significant challenges in extracting meaningful insights (Azzalini, et al, 2012). There is no universally accepted, unified process for analyzing the structure of mining methods; the problem-solving approach and its associated steps often vary from one case to another and from one analyst to another (Sharda et al., 2020). While essential steps such as data collection and preprocessing are critical prior to analysis, the inherent diversity in these steps may reveal unique structural characteristics for each study (Kumar et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2014\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eIn this study, we used a sequential text analysis process to develop a social network analysis methodology that benefits from machine learning techniques, specifically supervised sentiment analysis, alongside algorithms such as network analysis to extract valuable insights from tweets (microblogs). Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates the core stages of the current study\u0026rsquo;s methodology.\u003c/p\u003e\u003cp\u003eThe process began with data collection, with a focus on obtaining highly representative data that effectively captures users\u0026rsquo; public opinions. In text mining, this corpus, referred to as the data source, may originate from microblogs, comments, academic articles, social media content, and other sources. For this study, a comprehensive set of user tweets and comments was extracted from the text-rich environment of the Twitter platform, along with associated metadata (such as date and time, likes, replies, retweets, links, and locations,) The dataset consisted of 134,147 tweets under the two hashtags (#رؤية_السعودية_2030 and #SaudiVision2030), with the earliest tweet dated April 21, 2016. The hashtags were officially adopted by the Vision\u0026rsquo;s account April 25, 2016, and data collection continued through the end of 2022.\u003c/p\u003e\u003cp\u003eThe second phase, data preprocessing, was essential to improve the data analysis. This phase holds significant importance because any errors made here\u0026mdash;known as \u0026ldquo;systematic errors\u0026rdquo;\u0026mdash;can have a negative impact on the analysis (Sharda et al., 2020). Preprocessing included the removal of empty tweets, duplicates, and tweets without any textual data, reducing the number of tweets to 108,436. Additional steps included removing emojis, replacing user mentions with the keyword \u0026ldquo;user,\u0026rdquo; and applying other standard preprocessing techniques.\u003c/p\u003e\u003cp\u003eAfter the data was prepared, machine learning algorithms were applied for sentiment analysis. We used three transformer-based sentiment analysis models: the Camel BERT model for Arabic, and the Cardiff models for English and multilingual texts (Barbieri et al., \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Barbieri et al., \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Inoue et al., \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). These models, along with appropriate text analyzers, converted the textual data into digital format, allowing effective sentiments classification of the tweets.\u003c/p\u003e\u003c/div\u003e"},{"header":"5. Results and Discussion","content":"\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e5.1 Results\u003c/h2\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e\u003ccolgroup cols=\"9\"\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=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"9\" nameend=\"c9\" namest=\"c1\"\u003e\u003cp\u003eTable\u0026nbsp;(1) Form of tweets about Saudi Vision 2030 during the study period\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTime period\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e(2016)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(2017)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e(2018)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(2019)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e(2020)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e(2021)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e(2022)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"9\" nameend=\"c9\" namest=\"c1\"\u003e\u003cp\u003eForm of Tweets\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLanguages\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"8\" nameend=\"c9\" namest=\"c2\"\u003e\u003cp\u003e1- Arabic 2- English 3- Urdu 4- Other\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTweets\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e92272\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e12510\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e12608\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12947\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15368\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e43565\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e36403\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e225673\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccounts\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e40830\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5444\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4974\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e5194\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e13213\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e8185\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e83842\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLikes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e313752\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e99697\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e127451\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e167224\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e170545\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e387958\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e445147\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1711774\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eReplies\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e78864\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e22526\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e26850\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e51028\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e38534\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e73214\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e85810\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e376826\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRetweets\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e651470\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e156726\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e135121\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e140390\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e123453\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e269221\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e283182\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e1759563\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInteraction\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1044086\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e278949\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e289422\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e358642\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e332532\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e730393\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e814139\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e3848163\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\u003cb\u003eTable\u0026nbsp;(1)\u003c/b\u003e shows the format of tweets of Saudi Vision 2030 during the study period, represented by the number of tweets published from 2016 to 2022, totaling 225,673 tweets, posted by 83,842 accounts, with 1,711,774 likes, 376,826 replies, 1,759,563 retweets, and 3,848,163 total interactions. These tweets were written in four different languages over the course of the study.\u003c/p\u003e\u003cp\u003eA closer look at the data in Table\u0026nbsp;(1) reveals that the highest volume of tweets appeared in 2016, the launch year of Vision 2030, with 92,272 tweets, compared to only 12,510 tweets in 2017, which was the lowest number across the seven years studied. This spike in 2016 may be attributed to the intensive media campaigns that accompanied the launch of the Vision in its first year, along with strong public engagement and participation.\u003c/p\u003e\u003cp\u003eThe table also shows that the highest number of likes for Vision 2030 programs was in 2022, totaling 445,147 likes. This indicates positive outcomes and achievements seven years after the launch of the Vision. Similarly, the highest number of replies appeared in 2022, which suggests a more mature public understanding of the goals and programs of Vision 2030.\u003c/p\u003e\u003cp\u003eOn the other hand, the retweet peaked in 2016, totaling 651,470, reflecting strong public interaction and engagement with the Vision and its various programs. The overall interaction with the hashtags was especially notable in the first year of the Vision, reaching 1,044,086.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabb\" border=\"1\"\u003e\u003ccolgroup cols=\"9\"\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=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"9\" nameend=\"c9\" namest=\"c1\"\u003e\u003cp\u003eTable\u0026nbsp;(2) Multimedia content of tweets about Saudi Vision 2030 during the study period\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTime period\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e(2016)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(2017)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e(2018)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(2019)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e(2020)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e(2021)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e(2022)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"9\" nameend=\"c9\" namest=\"c1\"\u003e\u003cp\u003eMultimedia Content of Tweets\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImages\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e6334\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e8375\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e8328\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e9052\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e28194\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e26143\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e109610\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVideos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e980\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e864\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e967\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1117\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1548\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e3672\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e3685\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e12833\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLinks\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e16805\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e3289\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2923\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2209\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e2833\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12755\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e12627\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e53441\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMentions\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e15772\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4368\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e7485\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e8425\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e10477\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e16168\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e14732\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e77427\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHashtags\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e10589\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e6419\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e7494\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e7198\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e10173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e15766\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e13294\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e70933\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\u003eTable\u0026nbsp;(2) shows the multimedia content of tweets related to Saudi Vision 2030 during the study period. The total number of accompanying images in Vision 2030-related tweets reached 109,610 images, 12,833 video clips, 53,441 links and references to other web pages and sites, 77,427 user mentions, and 70,933 hashtags.\u003c/p\u003e\u003cp\u003eA closer look at Table\u0026nbsp;(2) shows that the most prominent use of images occurred during 2021 and 2022, indicating the multiplicity of projects implemented as part of Vision 2030 programs. This finding is further supported by the high number of video clips posted in the same period, totaling 3,672 videos in 2021 and 3,685 in 2022.\u003c/p\u003e\u003cp\u003eHashtag usage also reached its highest level in 2021 with 15,766 hashtags, followed by 13,294 hashtags in 2022, reflecting a peak in user engagement and dissemination of Vision 2030-related content during those years.\u003c/p\u003e\u003cp\u003e\u003cb\u003eTable\u0026nbsp;(3) Hashtag data analyzed in the study\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabc\" border=\"1\"\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" 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=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eHashtags\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eRaw Data\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eProcessed Data\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eرؤية_السعودية_2030\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e240644\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e90.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e204791\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e90.75\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSaudivision2030\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e26347\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e9.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e20882\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e9.25\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTotal\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e266991\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e225673\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\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\u003eThe data in Table\u0026nbsp;(3) illustrates the hashtags analyzed on platform (X), specifically the hashtag (#رؤية_السعودية_2030). During the 7-year study period, the total number of tweets reached 266,991, of which 240,644 tweets (representing 90.13%) were under the Arabic hashtag (#رؤية_السعودية_2030), while 26,347 tweets (or 9.87%) were under the English hashtag (#Saudivision2030).\u003c/p\u003e\u003cp\u003eExamining the data before the cleaning process reveals that there were 204,791 tweets under the Arabic hashtag (#رؤية_السعودية_2030), and 20,882 tweets under the English hashtag (#Saudivision2030).\u003c/p\u003e\u003cp\u003e\u003cb\u003eTable\u0026nbsp;(4) Language used in tweets about Saudi Vision 2030 during the study period\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabd\" border=\"1\"\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" 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\u003eLanguage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eArabic\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e210812\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e93.41\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eEnglish\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13363\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5.92\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eUrdu\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e238\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.11\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOther\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1260\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTotal\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e225673\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\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\u003eTable\u0026nbsp;(4) shows the languages used in tweets posted under the Vision 2030 hashtags \u0026mdash; #رؤية_السعودية_2030 (in Arabic) and #Saudivision2030 (in English) \u0026mdash; on platform (X) during the study period from April 25, 2016, to December 31, 2022.\u003c/p\u003e\u003cp\u003eTweets were written in three main languages as follows:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eArabic: 93.41%\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eEnglish: 5.92%\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eUrdu: 0.11%\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eOther languages: 0.56%\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eThis reflects the strong dominance of Arabic content in discussions around Saudi Vision 2030.\u003c/p\u003e\u003cp\u003e\u003cb\u003eTable\u0026nbsp;(5) Sentiment orientation of tweets about Saudi Vision 2030 during the study period\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabe\" border=\"1\"\u003e\u003ccolgroup cols=\"3\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" 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\u003eSentiment\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePositive\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e113522\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e50,3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNegative\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e28468\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12,6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNeutral\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e83683\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e37\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTota\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e225673\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\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\u003eTable\u0026nbsp;(5) presents the sentiment trends of tweets under the Saudi Vision 2030 hashtags. Positive sentiment ranked first, with 113,522 occurrences, representing 50.3% of the total. In comparison, neutral sentiment appeared 83,683 times (or 37%), while negative sentiment was the least frequent, with 28,468 occurrences (12.6%).\u003c/p\u003e\u003cp\u003eThese results indicate that positive sentiment dominates the tweets discussing Vision 2030 programs, suggesting broad public support for the initiative among Twitter users. Many individuals express their endorsement of Vision 2030 due to its ambitious goals focused on diversifying the economy, enhancing quality of life, and promoting social development. Positive engagement is especially evident in reaction to major initiatives launched under the Vision such as the NEOM and Qiddiya projects.\u003c/p\u003e\u003cp\u003eThe high percentage of positive sentiment also reflects hope and optimism for the future promised by the Vision, especially regarding job creation, women\u0026rsquo;s empowerment, and improvements to infrastructure and services. Vision 2030 is built upon three main pillars:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eA vibrant society,\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eA thriving economy,\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAnd an ambitious nation.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eThese pillars are interconnected and aligned to achieve national goals. The Vision Realization Programs (VRPs) serve as the driving force behind the implementation of Vision 2030, translating strategic objectives into tangible outcomes. Each program acts as a detailed roadmap, tailored through approved execution plans, guided by predefined goals and Key Performance Indicators (KPIs) over a five-year timeline.\u003c/p\u003e\u003cp\u003eAs Vision 2030 has evolved, some realization programs have been restructured to meet changing needs, reflect the kingdom\u0026rsquo;s ambitions and capabilities, and ensure full realization of the Vision. Key goals include reducing unemployment from 11.6\u0026ndash;7%, increasing non-oil exports to 50% of non-oil GDP (up from 16%), and boosting local production from 40% to approximately 65%, in collaboration with the private sector.\u003c/p\u003e\u003cp\u003eMeanwhile, neutral sentiment, which made up 37% of tweets, reflects balanced or observational perspectives, where users provided commentary or assessments of Vision 2030 without clear bias. These tweets often contain informational content or updates about projects without strong personal opinions.\u003c/p\u003e\u003cp\u003e\u003cb\u003eTable\u0026nbsp;(6) Sentiment orientation of tweets about Saudi Vision 2030 during the study period\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Tabf\" border=\"1\"\u003e\u003ccolgroup cols=\"16\"\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=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c14\" colnum=\"14\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c15\" colnum=\"15\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c16\" colnum=\"16\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eYear\u003c/p\u003e\u003cp\u003eSentiments\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e2016\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003e2017\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003e2018\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u003cp\u003e2019\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u003cp\u003e2020\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u003cp\u003e2021\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c15\" namest=\"c14\"\u003e\u003cp\u003e2022\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c16\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c12\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c13\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c14\"\u003e\u003cp\u003eF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c15\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePositive\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e48659\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e52.73\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6207\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e49.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6363\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e50.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e7014\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e54.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e8322\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e54.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e19700\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e45.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e17257\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e47.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e113522\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNegative\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e14357\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e15.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1641\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e13.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1658\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e13.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1682\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e12.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e2125\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e13.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e3823\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e8.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e3182\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e8.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e28468\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNeutral\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e29256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31.71\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4662\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e37.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e4587\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e36.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4251\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e32.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e4921\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e32.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e20042\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e15964\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e43.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e83683\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTota\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003e92272\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003e12510\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003e12608\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u003cp\u003e12947\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u003cp\u003e15368\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u003cp\u003e43565\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c15\" namest=\"c14\"\u003e\u003cp\u003e36403\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e225673\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\u003cb\u003eTable\u0026nbsp;(6)\u003c/b\u003e reveals the sentiment trends of tweets under the two hashtags related to Saudi Vision 2030 over the seven-year study period. The data shows that positive sentiments ranked first, with 113,522 occurrences, representing 50.3% of the overall tweet sentiments. Neutral sentiments came in second, with 83,683 occurrences (accounting for 37%), while negative sentiments ranked last, with 28,468 occurrences (representing 12.6%).\u003c/p\u003e\u003cp\u003eThese results indicate that the predominant sentiment among Twitter users toward Vision 2030 is positive, reflecting a widespread sense of approval among the Saudi public. This is largely due to the bold and comprehensive economic and social programs that Vision 2030 encompasses. These various programs aim to create a qualitative transformation in the cultural, social, and economic life of the Kingdom, positioning sustainable development as both the launching point and the ultimate goal in the Kingdom's journey toward joining the ranks of advanced nations.\u003c/p\u003e\u003cp\u003eRecognizing that human capital is the foundation and central focus of all development efforts, Vision 2030 emphasizes that the true wealth of the nation lies in its people, rooted in their Arab and Islamic identity and their noble values.\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003e\u003cb\u003eFigure (2) Sentiment trends of tweets about Saudi Vision 2030 during the study period\u003c/b\u003e\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"BlockQuote\"\u003e\u003cp\u003e\u003cb\u003eFigure (2)\u003c/b\u003e reveals the sentiment trends of tweets under the Saudi Vision 2030 hashtags during the study period. The data clearly shows the dominance of positive sentiment over other sentiment categories throughout the years of analysis.\u003c/p\u003e\u003cp\u003eSince the launch of Vision 2030, all state institutions have been required to unite efforts to realize its goals by reviewing their plans and programs in alignment with the Vision\u0026rsquo;s strategic objectives. This strong institutional commitment, reflected in the data, demonstrates the Saudi society\u0026rsquo;s engagement and interest in the Vision and its diverse programs.\u003c/p\u003e\u003cp\u003eMoreover, the prevalence of positive sentiment highlights public support for the achievements of Vision 2030 across various domains\u0026mdash;economic, social, cultural, political, and beyond\u0026mdash;reinforcing the Vision\u0026rsquo;s role as a comprehensive roadmap for sustainable development in the Kingdom.\u003c/p\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (3) Network analysis of Saudi Vision 2030 hashtags in 2016\u003c/b\u003e\u003c/p\u003e\u003cp\u003eIt is clear from the network graph (3) that sentiments and public attitudes toward the most frequently used hashtags accompanying \"رؤية_السعودية_2030\" in 2016 were almost entirely positive, as also shown by the results of Table\u0026nbsp;(5). This is reflected in the green lines that indicate a positive trend toward the programs of Saudi Vision 2030. The graph also reveals the notable density and thickness of the nodes between the main hashtag, \"رؤية_السعودية_2030\", at the center of the graph, and the hashtags (محمد_بن_سلمان), (التحول الوطني), (saudivision2030), and (السعودية). In social media network analysis, the nodes and the thickness of their connecting lines show the associations and strength of relationships between different hashtags. In this case, the graph shows how these hashtags are closely linked to discussions around \"رؤية المملكة 2030\" as the main hashtag.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (4) Network analysis of the Saudi Vision hashtags in 2017\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe network graph (4) reveals that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag \"رؤية_السعودية_2030\" in 2017 were mostly positive, as also shown by the results of Table\u0026nbsp;(6). This is reflected in the green lines that indicate a positive trend toward the programs of Saudi Vision 2030. We also observe the density and proximity of the nodes between the main hashtag \"رؤية_السعودية_2030\" at the center of the graph and the English version of the hashtag \"saudivision2030\", as well as hashtags like \"رؤية 2030\", \"السعودية\", and \"التحول الوطني\", indicating a strong overlap and frequent use of accompanying hashtags by users on the (X) platform. This also applies to other hashtags associated with the main hashtag, such as: (ولي العهد\", \"ريادة\", \"التحول الوطني\", \"مشروع نيوم\", \"مشروع البحر الاحمر\", \"الاخبارية\", \"التعليم\", and \"سياحة\" ) with varying levels of intensity. The emergence of projects like NEOM, the Red Sea Project, tourism, and entrepreneurship marked success and coincided with the launch of Saudi Vision 2030 on April 25, 2016.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (5) Network analysis of Saudi Vision hashtags in 2018\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe network graph (5) illustrates the network analysis of the Saudi Vision hashtags in 2018, showing that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag \"رؤية_السعودية_2030\" in 2018 were characterized by positivity, as also demonstrated by the results of Table\u0026nbsp;(7). This is reflected in the green lines and network nodes that indicate the prevailing positive orientation toward the programs of Saudi Vision 2030. The graph also shows the density and closeness of nodes between the hashtag \"رؤية_السعودية_2030\" at the center and hashtags such as \"السعودية\", \"ولي العهد\", \"محمد بن سلمان\", \"الرياض\", \"علاقة الجامعة بالمجتمع\", \"جامعة الجوف\", and \"اليوم الوطني\", indicating alignment and integration in the use of accompanying hashtags by users on the (X) platform. This also applies to other hashtags that have secondary connections with the main hashtag, such as: \"برنامج جودة الحياة\", \"التحول الرقمي\", \"ksa\", \"saudivision2030\", \"saudiarabia\", \"التأمين\", \"أتمنى\", and \"مجلة عين المملكة\", with varying degrees of intensity. The emergence of projects like NEOM, the Red Sea Project, tourism, and entrepreneurship marked success that coincided with the early launch of Saudi Vision 2030 on April 25, 2016.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (6) Network analysis of the Saudi Vision hashtags in 2019\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe network graph (6) illustrates the network analysis of the Saudi Vision hashtags in 2019. The data reveals that public sentiments and attitudes toward the most frequently used hashtags accompanying the hashtag \"رؤية_السعودية_2030\" in 2019 were positive, as also demonstrated by the results of Table\u0026nbsp;(9). This is reflected in the green lines, whether in the main nodes or the sub-nodes, which indicate unified positive sentiments toward the programs of Saudi Vision 2030. The graph also shows the density and closeness of the nodes between the hashtag \"رؤية_السعودية_2030\", which is at the center, and the hashtags (السعودية), (علاقة الجامعة بالمجتمع), (جامعة الجوف), (ولي العهد), and (محمد بن سلمان), indicating a strong alignment and frequent use of the accompanying hashtags by users on the (X) platform along with \"رؤية_السعودية_2030\". This also applies to other sub-hashtags connected to the main hashtag, such as: (برنامج جودة الحياة), (التحول الرقمي), (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), and (السعودية), with varying densities and node sizes. These hashtags represent the names of programs or topics related to the initiatives taken under Saudi Vision 2030.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (7) Network analysis of Saudi Vision hashtags in 2020\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe network graph (7) reveals the network analysis of the Saudi Vision hashtags in 2020. The main and sub-nodes in the figure show that the attitudes of Twitter users were aligned with the main hashtag of the study, \"رؤية_السعودية_2030\", reflecting positive sentiments toward the content of these hashtags. A closer look at the data in Figure (7) shows that there are major nodes represented by green lines for hashtags that align with the content and direction of the main hashtag \"رؤية_السعودية_2030\", such as: (السعودية العظمى), (السعودية), (علاقة الجامعة بالمجتمع), (ولي العهد), and (محمد بن سلمان), with varying densities and node sizes. The figure also reflects the density and closeness of nodes between the central main hashtags and the peripheral hashtags such as (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), (السعودية), and (برنامج جودة الحياة). This indicates the alignment and intensity of accompanying hashtag usage by users on the (X) platform alongside the hashtag \"رؤية_السعودية_2030\", with varying densities and connections. These hashtags represent names of programs or topics related to those programs included in Saudi Vision 2030.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (8) Network analysis of the Saudi Vision hashtags in 2021\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThe network graph (8) reveals the network analysis of the Saudi Vision hashtags in 2021. The main and sub-nodes in the graph show that the attitudes of Twitter users were aligned with the main hashtag \"رؤية_السعودية_2030\u0026rdquo; and were predominantly positive toward the content of these hashtags. A closer look at the data in Figure (8) shows that there are major and minor nodes represented by green lines for hashtags that align with the content and direction of the hashtag \"رؤية_السعودية_2030\", such as: (السعودية), (السعودية العظمى), (خادم الحرمين), (ولي العهد), (رؤية 2030 واقع يتحقق), (ksa), (saudivision2030), (saudiarabia), (التأمين), (أتمنى), (السعودية), and (برنامج جودة الحياة), with varying densities and node strengths. This indicates a strong alignment and intensity in the use of accompanying hashtags by users on the (X) platform along with the hashtag \"رؤية_السعودية_2030\", across different densities and connections.\u003c/p\u003e\u003cp\u003e\u003cb\u003eFigure (9) Network analysis of the Saudi Vision hashtags in 2022\u003c/b\u003e\u003c/p\u003e\u003cp\u003eThe data in Figure (9) presents the network analysis of the Saudi Vision hashtags in 2022. The network diagram reveals that the main and sub-nodes indicate that the attitudes of Twitter users aligned with the main hashtag \"رؤية_السعودية_2030\", with most sentiment directions characterized by positivity toward the content of these hashtags.\u003c/p\u003e\u003cp\u003eA closer look at the data in Figure (9) shows that most of the main and sub-nodes appeared as green lines representing hashtags that align with the content and direction of the main study hashtag, such as: (مجلس الوزراء), (برنامج جودة الحياة), (الرياض), (برنامج التحول الوطني), (اليوم الوطني السعودي), (محمد_بن_سلمان), (saudivision2030), (saudiarabia), (ولي العهد), (الرياض), (السعودية), and (جودة الحياة), with varying node densities and strengths. This indicates a strong alignment and high frequency of use of accompanying hashtags by users on the (X) platform along with the hashtag \"رؤية_السعودية_2030\".\u003c/p\u003e\u003cp\u003eAdditionally, the table reveals one negative sentiment connection between the hashtag \"رؤية_السعودية_2030\" and the hashtag \"صحيفة_واصل\", as highlighted by a red line in the node connecting the two hashtags. This, similar to the 2021 analysis, may suggest some criticism raised by the newspaper regarding delays in implementing certain projects related to the Saudi Vision 2030 programs.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003e5.2 Discussion and Conclusion:\u003c/h2\u003e\u003cp\u003eThe importance of this study emerges from the importance of the topic itself: analyzing social networks and identifying solutions and future perspectives to help evaluate the sustainability of Saudi Vision 2030. This study also helps in gaining insights that contribute to improving and accelerating the Vision\u0026rsquo;s goals. It showed that the use of modern tools and algorithms, including artificial intelligence for big data analysis, contributes to the development of research in new media and social networks. In addition to its scientific contribution in employing advanced algorithms for descriptive analysis, network analysis, and sentiment analysis, this study contributes to drawing the attention of researchers and specialists in the fields of new media and social networks toward conducting similar studies.\u003c/p\u003e\u003cp\u003eIn what follows discussion of the findings of the current study:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eTable\u0026nbsp;(1) shows that the highest number of tweets appeared in 2016, the year Saudi Vision 2030 was launched, with (92,272) tweets. This increase is probably attributed to the intensive media campaigns that accompanied the launch of the Vision in its first year, and the resulting interactions and participation from the user audience. As shown in the table, the highest number of likes on Vision 2030 programs was in 2022, with (445,147) likes, indicating positive results and achievements realized after 7 years. The highest number of replies to tweets was in 2022, suggesting a more mature public understanding of the Vision\u0026rsquo;s programs and goals. In contrast, the most retweets, (651,470), were recorded in 2016, indicating the Saudi public\u0026rsquo;s immediate engagement with the Vision and its programs. Hashtag interaction was also prominent and clear in the launch year with 1,044,086 interactions.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eTable\u0026nbsp;(5) reveals the dominance of positive sentiment toward the programs of Vision 2030, indicating the Saudi society's strong acceptance of the Vision\u0026rsquo;s programs and the accompanying transformations across various economic, social, and cultural levels, ultimately leading toward sustainable development.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eFigures (3\u0026ndash;4) show the strong correlations between highly significant hashtags such as: \"السعودية\", \"التحول الوطني\", and \"محمد بن سلمان\" as sub-hashtags within the programs of Vision 2030. This can be explained by several factors:\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eDirect relationship with the Vision\u003c/b\u003e: Crown Prince Mohammed bin Salman is considered the driving force behind Saudi Vision 2030. Therefore, there is a natural and strong association between the hashtag \"رؤية المملكة 2030\" and \"محمد بن سلمان\", as his name is frequently mentioned in discussions about the Vision and its initiatives.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eNational development initiative\u003c/b\u003e: Vision 2030 is a national initiative aimed at developing and enhancing various sectors in Saudi Arabia. As such, the hashtag \"السعودية\" is closely linked to \"رؤية المملكة 2030\" in the context of discussions around national development and progress.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003e\"National Transformation Program\" (NTP)\u003c/b\u003e: This is a fundamental component of Vision 2030, aiming to achieve the Vision\u0026rsquo;s goals through a variety of reforms across government, economy, and society. Therefore, the hashtag \"التحول الوطني\" is directly connected to the hashtag \"رؤية المملكة 2030\".\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eShared events and initiatives\u003c/b\u003e: New initiatives and programs are often launched under the umbrella of Vision 2030, and these frequently include references to the Crown Prince or other subprograms such as \"التحول الوطني\". This leads to joint engagement with these hashtags, further strengthening their connection in network analysis.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eFocus of official and media discourse\u003c/b\u003e: The official and media discourse in Saudi Arabia tends to employ certain hashtags to reinforce specific messages. When discussing Vision 2030, it is commonly linked to leadership figures such as (محمد بن سلمان) and to key initiatives like (التحول الوطني), which reinforces their connection.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eTable\u0026nbsp;(3) highlights the prominence of images, mentions, and hashtags in the multimedia content of tweets related to Saudi Vision 2030. This can be interpreted as follows:\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eAttracting attention\u003c/b\u003e: Images usually attract more attention than plain text. Users tend to engage more with tweets that contain images or visual media. Therefore, the use of images could be an effective strategy to draw more attention to tweets related to the Vision.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eEngagement and reach\u003c/b\u003e: Hashtags are typically used to organize content, while mentions are employed to increase the reach of tweets. When hashtags and mentions associated with Saudi Vision are used, tweets can reach larger segments of users interested in the topic, increasing the chances of interaction and sharing.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eShift toward digital marketing\u003c/b\u003e: With the evolution of social media, governments and institutions have come to recognize the importance of digital marketing for reaching audiences. Using images, hashtags, and mentions is part of effective communication strategies on these platforms.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eTable\u0026nbsp;(4) reveals the predominant use of the Arabic language in the hashtags and tweets about the Vision 2030 compared to English. This is due to the following:\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003col\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eTarget audience\u003c/b\u003e: The primary target audience of Vision 2030 is the citizens and residents of Saudi Arabia, who mainly speak Arabic. Since it is a national initiative aiming for comprehensive development within the Kingdom, Arabic is naturally the main language used.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eCultural identity reinforcement\u003c/b\u003e: Using Arabic reflects the national and cultural identity of Saudi Arabia. The Vision aims to strengthen the Kingdom\u0026rsquo;s cultural and social identity, making the use of Arabic in hashtags an effective tool to support this goal.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eClarity and interaction\u003c/b\u003e: Most Twitter users in Saudi Arabia speak Arabic. Using Arabic in hashtags makes the content clearer and easier to understand for local users, resulting in higher engagement.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eDirect communication with citizens\u003c/b\u003e: Government initiatives often use Arabic to communicate with citizens to ensure messages and policies are delivered clearly and directly.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003cspan\u003e\u003cli\u003e\u003cp\u003e\u003cb\u003eLocal outreach\u003c/b\u003e: Arabic-language hashtags allow tweets to reach users across the Arab world, increasing their visibility both locally and regionally.\u003c/p\u003e\u003c/li\u003e\u003c/span\u003e\u003c/ol\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eStudy Recommendations\u003c/b\u003e:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eThe study recommends using Large Language Models (LLMs) to analyze big data in social networks instead of classification models, as LLMs have higher capabilities in interpreting texts and words.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe study recommends conducting research that involves large-scale data using artificial intelligence algorithms and developing new research methods and tools for digital media analysis.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe study calls on researchers and those interested in AI technologies to explore, standardize, and use modern techniques in the media field. Integrating these methods can lead to more accurate and comprehensive results.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe study recommends using the Knowledge Graph application for representing and extracting information from textual data. This application provides a clearer and more accurate representation of network relationships.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eFuture Research Directions\u003c/b\u003e:\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eFuture research can expand its focus by using the methodology applied in this study to qualitative data analysis, including short blogs. It is not necessarily required to follow this methodology exactly; it can be adapted by updating AI models for sentiment analysis and topic modeling, and even by modifying parts of it.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThis research helps clarify the methodology of social network analysis, from data collection to analysis and presentation, highlighting the need for further studies and research.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003ch2\u003eThe funding statements:\u003c/h2\u003e\u003cp\u003eThis work was supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University (IMSIU) (grant number IMSIU-DDRSP2502)\u003c/p\u003e\u003ch2\u003eConflicts of Interest:\u003c/h2\u003e\u003cp\u003eThe author declares no conflicts of interest.\u003c/p\u003e\u003ch2\u003eDisclaimer/Publisher\u0026rsquo;s Note:\u003c/h2\u003e\u003cp\u003eThe statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to\u003c/p\u003e\u003cp\u003epeople or property resulting from any ideas, methods, instructions or products referred to in the content.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eContributionsMohammad Ali Alquaary wrote the main manuscript tex, Alquaary prepared figures and tables. author reviewed the manuscript.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAl-Areeshi J, Saleh F (2020) The use of big data and artificial intelligence in confronting the emerging coronavirus pandemic. Arab J Secur Stud 36(2):249\u0026ndash;264. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.26735/GYCX5740\u003c/span\u003e\u003cspan address=\"10.26735/GYCX5740\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Khalifi T (2019) Social media data mining and its uses in media research: Sentiment analysis as a model. J Media Res Stud 8(8):1\u0026ndash;73. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/mjsm.2019.109622\u003c/span\u003e\u003cspan address=\"10.21608/mjsm.2019.109622\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Qahtani LA, Al-Mutairi SM, Al-Juhani AS (2024) The role of Saudi digital media in raising citizen awareness of cybercrime techniques in the Kingdom of Saudi Arabia. J Arts Literature Humanit Social Sci 104:283\u0026ndash;327. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.33193/JALHSS.104.2024.1085\u003c/span\u003e\u003cspan address=\"10.33193/JALHSS.104.2024.1085\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Shaddi TA (2010) Social network analysis methodology. King Saud Univ Journal: Arts 22(2):373\u0026ndash;403. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://search.mandumah.com/Record/478946\u003c/span\u003e\u003cspan address=\"https://search.mandumah.com/Record/478946\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Thaqafi IM (2020) Journalistic coverage of G20 issues in light of Saudi Vision 2030. Egypt J Media Res 76:1\u0026ndash;46. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/ejsc.2021.194421\u003c/span\u003e\u003cspan address=\"10.21608/ejsc.2021.194421\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Toukhi MM (2018) The dependence of Saudi university students on electronic newspapers for Saudi Vision 2030: A case study. Sci J Journalism Res 15:273\u0026ndash;334. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/sjsj.2018.155194\u003c/span\u003e\u003cspan address=\"10.21608/sjsj.2018.155194\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAl-Zahrani AA, Salem DF (2018) The role of social media in the formation of Saudi youth attitudes towards the Kingdom's 2030 vision. Egypt J Media Res 2018(65):193\u0026ndash;279. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/ejsc.2018.86777\u003c/span\u003e\u003cspan address=\"10.21608/ejsc.2018.86777\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAli AKA (2018) Big data and its analytics: Concept, characteristics, and applications. J Fac Arts 49(2):445\u0026ndash;476. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/bfa.2018.188153\u003c/span\u003e\u003cspan address=\"10.21608/bfa.2018.188153\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAlkathiri ES (2020) The relationship between Saudi citizen perceptions of Vision 2030 and Saudi government social media use to promote Vision 2030 [Doctoral dissertation, University of North Dakota]. UND Scholarly Commons. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://commons.und.edu/theses/3364\u003c/span\u003e\u003cspan address=\"https://commons.und.edu/theses/3364\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAlsaaidi HZ (2020) Nation branding and the case of Saudi Vision 2030 and the use of Twitter [Master's thesis, Rochester Institute of Technology]. RIT Digital Media Library. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://repository.rit.edu/theses/10615\u003c/span\u003e\u003cspan address=\"https://repository.rit.edu/theses/10615\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAmato G, Behrmann M, Bimbot F, Caramiaux B, Falchi F, Garcia A, Geurts J, Gibert J, Gravier G, Holken H, Koenitz H, Lefebvre S, Liutkus A, Lotte F, Perkis A, Redondo R, Turrin E, Vieville T, Vincent E (2019) \u003cem\u003eAI in the media and creative industries\u003c/em\u003e [White paper]. arXiv. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.48550/arXiv.1905.04175\u003c/span\u003e\u003cspan address=\"10.48550/arXiv.1905.04175\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAzzalini A, Scarpa B (2012) Data Analysis and Data Mining: an Introduction. OUP USA\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBadran MH (2019) The impact of Big Data analytics on the efficiency of marketing campaign [Master's thesis, Syrian Virtual University]\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBarbieri F, Anke LE, Camacho-Collados J, Kar S, Segura-Bedmar I, Kann K, Nakov P (2022) XLM-T: Multilingual language models in Twitter for sentiment analysis and beyond. arXiv preprint. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.48550/arXiv.2104.12250\u003c/span\u003e\u003cspan address=\"10.48550/arXiv.2104.12250\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBarbieri F, Camacho-Collados J, Anke E, L., Neves L (2020) TweetEval: Unified benchmark and comparative evaluation for tweet classification. In \u003cem\u003eFindings of the Association for Computational Linguistics: EMNLP 2020\u003c/em\u003e (1644\u0026ndash;1650). Association for Computational Linguistics. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://aclanthology.org/2020.findings-emnlp.148\u003c/span\u003e\u003cspan address=\"https://aclanthology.org/2020.findings-emnlp.148\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCheng G (2018) \u003cem\u003eArtificial intelligence in media industries: Creating better user experiences and maintaining high customer loyalties\u003c/em\u003e [Master's thesis, Drexel University]. Drexel Digital Repository. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.17918/D87077\u003c/span\u003e\u003cspan address=\"10.17918/D87077\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEl-Sayed H (2021) Employing artificial intelligence applications to analyze social media users' sentiments in real-time during the COVID-19 crisis. Egypt J Public Opin Res 20(2):149\u0026ndash;202. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21608/joa.2021.190747\u003c/span\u003e\u003cspan address=\"10.21608/joa.2021.190747\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eElshereef SAMA (2022) Sentiment analysis for Twitter during U.S. Presidential Election2020 Using the big data framework. Egypt J Public Opin Res 21(2):1\u0026ndash;49. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/joa.2022.250344\u003c/span\u003e\u003cspan address=\"10.21608/joa.2022.250344\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFaraj A (2022) Investing big data to develop search and retrieval mechanisms and customize information institution services: A prospective study. Sci J Libr Documents Inform 4(11):7\u0026ndash;42. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/jslmf.2021.53697.1058\u003c/span\u003e\u003cspan address=\"10.21608/jslmf.2021.53697.1058\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHarfoush I, Al- Warqali S, Ba'di W (2019) The impact of robot anchors on the journalism profession: A semiological analytical study on a sample of news bulletins [Master's thesis, University of Ouargla]. DSpace Repository. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://dspace.univ-ouargla.dz/jspui/handle/123456789/21387\u003c/span\u003e\u003cspan address=\"http://dspace.univ-ouargla.dz/jspui/handle/123456789/21387\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIbrahim HG (2022) A prospective vision for adopting artificial intelligence technologies in Palestinian satellite channels. Algerian J Communication 24(1):8\u0026ndash;29. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://asjp.cerist.dz/en/article/189698\u003c/span\u003e\u003cspan address=\"https://asjp.cerist.dz/en/article/189698\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eInoue G, Alhafni B, Baimukan N, Almatham R et al (2021) The interplay of variant, size, and task type in Arabic pretrained language models. In Proceedings of the Sixth Arabic Natural Language Processing Workshop (WANLP 2021). Association for Computational Linguistics. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://arxiv.org/abs/2103.06678\u003c/span\u003e\u003cspan address=\"https://arxiv.org/abs/2103.06678\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJohnson TJ, Kaye BK (2015) Site effects: How reliance on social media influences confidence in the government and news media. Social Sci Comput Rev 33(2):127\u0026ndash;144. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/0894439314537029\u003c/span\u003e\u003cspan address=\"10.1177/0894439314537029\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKumar S, Morstatter F, Liu H (2014) Twitter Data Analytics. Springer, New York, NY\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eK\u0026uuml;mpel AS (2020) The Matthew Effect in social media news use: Assessing inequalities in news exposure and news engagement on social network sites (SNS). Journalism 21(8):1083\u0026ndash;1098. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/1464884920915374\u003c/span\u003e\u003cspan address=\"10.1177/1464884920915374\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMansour RAMA, Abdelrazek HMS (2017) The future of data journalism in Egypt during the next two decades 2017\u0026ndash;2037. J Mass Communication Res 120\u0026ndash;137. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/JKOM.2020.108647\u003c/span\u003e\u003cspan address=\"10.21608/JKOM.2020.108647\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMd Suhaimin MS, Ahmad Hijazi MH, Moung EG, Nohuddin PNE, Chua S, Coenen F (2023) Social media sentiment analysis and opinion mining in public security: Taxonomy, trend analysis, issues and future directions. J King Saud Univ - Comput Inform Sci 35(9):833\u0026ndash;838. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jksuci.2023.101776\u003c/span\u003e\u003cspan address=\"10.1016/j.jksuci.2023.101776\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNaskar D, Mokaddem S, Rebollo M, Onaindia E (2016) Sentiment analysis in social networks through topic modeling. \u003cem\u003eIn Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)\u003c/em\u003e. 46\u0026ndash;53. European Language Resources Association. https://aclanthology.org/L16-1008\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSanousi T (2021) Theories of new media. Arab Agency for Public Relations\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSawani FM (2016) Scientific research, 1st edn. Ibn Al-Nadim Publishing\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSharda R, Delen D, Turban E (2021) Analytics, data science, \u0026amp; artificial intelligence: Systems for decision support. Pearson Education Limited\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStatistics (2016) Social networking Garton Timmy. Grophlcsms. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.Grophlcsms,com/blog/877-social-networking statisties\u0026ndash;2010/ht\u003c/span\u003e\u003cspan address=\"http://www.Grophlcsms,com/blog/877-social-networking statisties\u0026ndash;2010/ht\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eThabet S, Thabet A (2022) J Financial Commercial Res 23(1):1\u0026ndash;40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21608/jsst.2021.102896.1340\u003c/span\u003e\u003cspan address=\"10.21608/jsst.2021.102896.1340\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. The impact of big data analytics on operational efficiency of banks using data envelopment analysis: Applied to Commercial International Bank\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTosun LP (2012) Motives for Facebook use and expressing true self on the Internet. Comput Hum Behav 28(4):1510\u0026ndash;1517. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.chb.2012.03.018\u003c/span\u003e\u003cspan address=\"10.1016/j.chb.2012.03.018\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZeki WR (2015) Theory of social networks: From ideology to methodology. The Arab Forum for Social and Human Sciences. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://socio.yoo7.com/t3886-topic\u003c/span\u003e\u003cspan address=\"https://socio.yoo7.com/t3886-topic\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"Saudi Vision 2030, network analysis, artificial intelligence, sentiment analysis, mixed-method analysis","lastPublishedDoi":"10.21203/rs.3.rs-7482610/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7482610/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study aimed to explore how artificial intelligence techniques can be utilized in the analysis of big data in relation to Saudi Vision 2030. Using methodologies such as network analysis and sentiment analysis, the study sought to provide in-depth insights into how Saudi Vision 2030 is perceived by the Saudi public, and to identify the aspects that garner the highest levels of attention, interaction, and engagement. The study focused on the Arabic hashtag (رؤية_السعودية_2030#) and the English hashtag (#SaudiVision2030) on the X platform, covering a seven-year period from 2016 to 2022. A mixed-method approach was adopted, combining traditional statistical analysis with network analysis techniques and natural language processing \u0026mdash; using artificial intelligence tools \u0026mdash; to gain a deeper understanding of public sentiment and the dominant topics in discussions surrounding Saudi Vision 2030. Tweets were categorized by sentiment into positive, negative, and neutral in order to assess the overall public mood toward the Vision and its diverse and comprehensive developmental goals, which fundamentally emphasize sustainability. Textual network analysis helped explore relationships among user opinions and responses to the Vision. The findings revealed that positive sentiment towards Vision 2030 programs was predominant, accounting for 50.3% of tweets, compared to 37% neutral and 12.6% negative sentiment. This indicates widespread support within Saudi society for the Vision and the economic, social, and cultural transformations it has introduced, all of which contribute to sustainable development. The study recommended the use of Large Language Models (LLMs) for big data analysis on social media platforms instead of traditional classification models, due to their superior capabilities in interpreting text and language. It also advised the application of Knowledge Graphs to represent and extract information from textual data, as this approach provides a clearer and more accurate representation of network relationships.\u003c/p\u003e","manuscriptTitle":"Employing Network Analysis of Big Data on Platform (X) in Relation to Saudi Vision 2030 (An Analytical Longitudinal Study for the Period from 2016–2022)","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-16 17:17:48","doi":"10.21203/rs.3.rs-7482610/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":"21db305d-74fe-4f9f-82c2-af95d0e05194","owner":[],"postedDate":"October 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-06T09:23:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-16 17:17:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7482610","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7482610","identity":"rs-7482610","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}