Identifying Students in Need of Psychological Support: An AI-Driven Approach Using Public Behavioral Data

Identifying Students in Need of Psychological Support: An AI-Driven Approach Using Public Behavioral Data | 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 Identifying Students in Need of Psychological Support: An AI-Driven Approach Using Public Behavioral Data Tingting Yao, Weijun Wang, Xin Zhao, Jian Xie, Juan Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6399521/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Background: Mental health challenges are increasingly prevalent among Chinese university students, as reflected in national reports and policy statements. How- ever, traditional psychological assessments,such as self-report scales, which often serve as the initial step in the psychological service process,are limited by issues of ecological validity, recall bias, and operational complexity, particularly when applied to large populations. Recent research suggests that public behavioral data may carry indirect signals of individuals’ psychological states, offering new possibilities for mental health monitoring beyond traditional tools. In this study, public behavioral data refers specifically to non-private, institutionally recorded behavioral records routinely collected by student governance departments,such as hygiene task participation, academic attendance, and disciplinary deductions,for administrative or educational management purposes. These records provide a non-intrusive and scalable means of assessing students’ psychological well-being in real-world settings. This study explores whether machine learning models can effectively identify students who may require psychological support using such publicly recorded behavioral data, providing a cost-effective and ethically feasible alternative to conventional screening methods. Methods: Behavioral and mental health data from 1,255 students at a Chi- nese university were collected with informed consent. Mental health assessments, based on the Chinese College Students’ Mental Health Scale, served as supervised labels, while public behavioral data,covering academic achievement and academic behavioral performance and compliance-related behaviors,were used as indepen- dent variables. Three typical supervised AI learning models (Logistic Regression, K-Nearest Neighbors, and LightGBM) were tested for classification performance. Notably, mental health scale data were only used during model training for label- ing purposes. Once the model was established, predictions could be made solely based on public behavioral data, without requiring any additional psychological assessments.In addition to the main classification task, two exploratory analyses were con- ducted. First, to identify the optimal behavioral observation window for predict- ing psychological support needs, we incrementally accumulated weekly behavioral data over a 17-week period and evaluated model performance at each time point using Accuracy, F1-score, and AUC. Second, to explore intra-individual vari- ability among students potentially in need of psychological support, we tracked their predicted probability scores over time based on weekly updates of dynamic features. Both analyses were implemented using the previously established Light- GBM model, with static features (e.g., demographic and academic performance) held constant while dynamic features (e.g., cumulative disciplinary deductions) were updated weekly. Results: LightGBM outperformed traditional classification algorithms (Logistic Regression and K-Nearest Neighbors) in identifying students potentially in need of psychological support, achieving an AUC of 0.972 and an F1-score of 0.875. In addition to robust classification performance, we found that model metrics peaked when behavioral data were cumulatively observed over a 15-week period. This suggests that approximately 15 weeks of behavioral accumulation may serve as an optimal observation window for identifying students requiring psychologi- cal support. Furthermore, prediction trajectories of individual students revealed notable fluctuations over time, highlighting the dynamic nature of psychologi- cal states and the potential for more personalized, time-sensitive mental health interventions. Conclusion: This study confirms that supervised machine learning can serve as a real-time alternative to traditional psychological assessment methods, enhancing the effciency of university counseling service departments . Additionally, two key findings emerged: (1) determining the minimum data collection period required for effective assessment of mental health status, optimizing university mental health service resource management; and (2) there are significant dynamic change patterns in the psychological states of students who may need psychological sup- port, providing crucial insights for more precise personalized interventions. Future research should explore the generalizability of these findings across different university settings and student populations. Psychology university mental health management AI students’ behavior data mental health monitoring Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-6399521","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":440392687,"identity":"42d7c8e4-8179-470d-ad12-caa4a171f77a","order_by":0,"name":"Tingting Yao","email":"","orcid":"","institution":"School of Psychology, Central China Normal University, Wuhan, China；Department of Information Technology (Cyber Surveillance), Hunan Police Academy, Changsha, China","correspondingAuthor":false,"prefix":"","firstName":"Tingting","middleName":"","lastName":"Yao","suffix":""},{"id":440392688,"identity":"5b740250-8c2d-46f3-8137-f869020726ae","order_by":1,"name":"Weijun Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYNACHhsGBmbmBhjXgBgtaUAtjCRpYTgMxMRqMTh+9vBrHpnz0fztQC0/au4kNrA3b5NgqLmDW8uZvDRrHp7buTMOMzYw9hx7ltjAc6xMguHYM5xazA7kmBnnALU0ALUAvXM4sUEix0wCyMCt5fwbkJZzufPhWuTfENByI8f4cQ7PgdwNCFt48Guxv/HGjPkPT3LuRqCWgz3HDhu38aQVWyQcw61Fsj/H+OPMHrvceecPH3zwo+awbD/74Y03PtTg1gIEbBKMPRDWATAXRCTg0wCM9g8MP/CrGAWjYBSMghEOABLVWKPc+mt2AAAAAElFTkSuQmCC","orcid":"","institution":"School of Psychology, Central China Normal University, Wuhan, China","correspondingAuthor":true,"prefix":"","firstName":"Weijun","middleName":"","lastName":"Wang","suffix":""},{"id":440392689,"identity":"155b7da5-5b6f-427d-8b4e-1af70a69ea5b","order_by":2,"name":"Xin Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIie2RMWvCQBiGXykkHc5mjQjeX7gQsEOp/SsXAt0Cha6BBgSnUFelg38hJeB8cHBTQtcWHYSCS5eAIIVKMYpT6xXHDvcMxwcvz937cYDB8B8h+1MAdnIYfkR/KEQcButkxeUnKjQtvAU2c+q0PoLVXTzv0ElfVYh7YIU4qrAy9RnI0hs/RXl7pJY+U1Y4ggrrKDmuOKTrwpWNbBZl7WYig8wift1OgL1oig3J5SeYvMneyvyrVh4mA2cFfOsVlGkX4PXlr83p7hUORc7QGAh9sULdu1zIcJxG0yuipJepWx/BY0hamvVpGj5X1UZeD+0yn5FYUtqX76jWvc5FwTXNzhl+R1z/kTX2Qp8ZDAaDYccWkiJiNRMlYtcAAAAASUVORK5CYII=","orcid":"","institution":"Manchester Institute of Education, The University of Manchester, UK","correspondingAuthor":true,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhao","suffix":""},{"id":440392690,"identity":"970ebea8-975f-402f-a320-1209d36d0a81","order_by":3,"name":"Jian Xie","email":"","orcid":"","institution":"Department of Information Technology (Cyber Surveillance), Hunan Police Academy, Changsha, China","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Xie","suffix":""},{"id":440392691,"identity":"4d06f54f-c00f-4f6a-a85d-a232fa2719b6","order_by":4,"name":"Juan Chen","email":"","orcid":"","institution":"Department of Information Technology (Cyber Surveillance), Hunan Police Academy, Changsha, China","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-04-08 05:45:50","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6399521/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-6399521/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81646420,"identity":"bec106e0-e3e2-4c36-a130-dabc22f7fd67","added_by":"auto","created_at":"2025-04-29 14:40:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1239304,"visible":true,"origin":"","legend":"","description":"","filename":"PreprintYaoMentalHealthML2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6399521/v2_covered_ee022dcf-faaa-4570-97ce-03217f2cf392.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Identifying Students in Need of Psychological Support: An AI-Driven Approach Using Public Behavioral Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"\"Central China Normal University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"university mental health management, AI, students’ behavior data, mental health monitoring","lastPublishedDoi":"10.21203/rs.3.rs-6399521/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6399521/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Mental health challenges are increasingly prevalent among Chinese\u003c/p\u003e\n\u003cp\u003euniversity students, as reflected in national reports and policy statements. How-\u003c/p\u003e\n\u003cp\u003eever, traditional psychological assessments,such as self-report scales, which often\u003c/p\u003e\n\u003cp\u003eserve as the initial step in the psychological service process,are limited by issues\u003c/p\u003e\n\u003cp\u003eof ecological validity, recall bias, and operational complexity, particularly when\u003c/p\u003e\n\u003cp\u003eapplied to large populations. Recent research suggests that public behavioral\u003c/p\u003e\n\u003cp\u003edata may carry indirect signals of individuals’ psychological states, offering new\u003c/p\u003e\n\u003cp\u003epossibilities for mental health monitoring beyond traditional tools. In this study,\u003c/p\u003e\n\u003cp\u003epublic behavioral data refers specifically to non-private, institutionally recorded\u003c/p\u003e\n\u003cp\u003ebehavioral records routinely collected by student governance departments,such as\u003c/p\u003e\n\u003cp\u003ehygiene task participation, academic attendance, and disciplinary deductions,for\u003c/p\u003e\n\u003cp\u003eadministrative or educational management purposes. These records provide a\u003c/p\u003e\n\u003cp\u003enon-intrusive and scalable means of assessing students’ psychological well-being\u003c/p\u003e\n\u003cp\u003ein real-world settings. This study explores whether machine learning models can\u003c/p\u003e\n\u003cp\u003eeffectively identify students who may require psychological support using such\u003c/p\u003e\n\u003cp\u003epublicly recorded behavioral data, providing a cost-effective and ethically feasible\u003c/p\u003e\n\u003cp\u003ealternative to conventional screening methods.\u003c/p\u003e\n\u003cp\u003eMethods: Behavioral and mental health data from 1,255 students at a Chi-\u003c/p\u003e\n\u003cp\u003enese university were collected with informed consent. Mental health assessments,\u003c/p\u003e\n\u003cp\u003ebased on the Chinese College Students’ Mental Health Scale, served as supervised\u003c/p\u003e\n\u003cp\u003elabels, while public behavioral data,covering academic achievement and academic\u003c/p\u003e\n\u003cp\u003ebehavioral performance and compliance-related behaviors,were used as indepen-\u003c/p\u003e\n\u003cp\u003edent variables. Three typical supervised AI learning models (Logistic Regression,\u003c/p\u003e\n\u003cp\u003eK-Nearest Neighbors, and LightGBM) were tested for classification performance.\u003c/p\u003e\n\u003cp\u003eNotably, mental health scale data were only used during model training for label-\u003c/p\u003e\n\u003cp\u003eing purposes. Once the model was established, predictions could be made solely\u003c/p\u003e\n\u003cp\u003ebased on public behavioral data, without requiring any additional psychological\u003c/p\u003e\n\u003cp\u003eassessments.In addition to the main classification task, two exploratory analyses were con-\u003c/p\u003e\n\u003cp\u003educted. First, to identify the optimal behavioral observation window for predict-\u003c/p\u003e\n\u003cp\u003eing psychological support needs, we incrementally accumulated weekly behavioral\u003c/p\u003e\n\u003cp\u003edata over a 17-week period and evaluated model performance at each time point\u003c/p\u003e\n\u003cp\u003eusing Accuracy, F1-score, and AUC. Second, to explore intra-individual vari-\u003c/p\u003e\n\u003cp\u003eability among students potentially in need of psychological support, we tracked\u003c/p\u003e\n\u003cp\u003etheir predicted probability scores over time based on weekly updates of dynamic\u003c/p\u003e\n\u003cp\u003efeatures. Both analyses were implemented using the previously established Light-\u003c/p\u003e\n\u003cp\u003eGBM model, with static features (e.g., demographic and academic performance)\u003c/p\u003e\n\u003cp\u003eheld constant while dynamic features (e.g., cumulative disciplinary deductions)\u003c/p\u003e\n\u003cp\u003ewere updated weekly.\u003c/p\u003e\n\u003cp\u003eResults: LightGBM outperformed traditional classification algorithms (Logistic\u003c/p\u003e\n\u003cp\u003eRegression and K-Nearest Neighbors) in identifying students potentially in need\u003c/p\u003e\n\u003cp\u003eof psychological support, achieving an AUC of 0.972 and an F1-score of 0.875.\u003c/p\u003e\n\u003cp\u003eIn addition to robust classification performance, we found that model metrics\u003c/p\u003e\n\u003cp\u003epeaked when behavioral data were cumulatively observed over a 15-week period.\u003c/p\u003e\n\u003cp\u003eThis suggests that approximately 15 weeks of behavioral accumulation may serve\u003c/p\u003e\n\u003cp\u003eas an optimal observation window for identifying students requiring psychologi-\u003c/p\u003e\n\u003cp\u003ecal support. Furthermore, prediction trajectories of individual students revealed\u003c/p\u003e\n\u003cp\u003enotable fluctuations over time, highlighting the dynamic nature of psychologi-\u003c/p\u003e\n\u003cp\u003ecal states and the potential for more personalized, time-sensitive mental health\u003c/p\u003e\n\u003cp\u003einterventions.\u003c/p\u003e\n\u003cp\u003eConclusion: This study confirms that supervised machine learning can serve as a\u003c/p\u003e\n\u003cp\u003ereal-time alternative to traditional psychological assessment methods, enhancing\u003c/p\u003e\n\u003cp\u003ethe effciency of university counseling service departments . Additionally, two key\u003c/p\u003e\n\u003cp\u003efindings emerged: (1) determining the minimum data collection period required\u003c/p\u003e\n\u003cp\u003efor effective assessment of mental health status, optimizing university mental\u003c/p\u003e\n\u003cp\u003ehealth service resource management; and (2) there are significant dynamic change\u003c/p\u003e\n\u003cp\u003epatterns in the psychological states of students who may need psychological sup-\u003c/p\u003e\n\u003cp\u003eport, providing crucial insights for more precise personalized interventions. Future\u003c/p\u003e\n\u003cp\u003eresearch should explore the generalizability of these findings across different\u003c/p\u003e\n\u003cp\u003euniversity settings and student populations.\u003c/p\u003e","manuscriptTitle":"Identifying Students in Need of Psychological Support: An AI-Driven Approach Using Public Behavioral Data","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2025-04-29 14:24:32","doi":"10.21203/rs.3.rs-6399521/v2","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}},{"code":1,"date":"2025-04-09 04:46:52","doi":"10.21203/rs.3.rs-6399521/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":"2dbd2bd4-4646-4547-90ce-e66f580e6c70","owner":[],"postedDate":"April 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46884427,"name":"Psychology"}],"tags":[],"updatedAt":"2025-04-09T04:46:52+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-29 14:24:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-6399521","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6399521","identity":"rs-6399521","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}