AI-Supported Lifelong Learning: Predicting Digital Competence and Learner Profiles with PIAAC Turkey Data

AI-Supported Lifelong Learning: Predicting Digital Competence and Learner Profiles with PIAAC Turkey 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 AI-Supported Lifelong Learning: Predicting Digital Competence and Learner Profiles with PIAAC Turkey Data Nihan OZBALTAN This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8238956/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Purpose: Although AI offers enormous potential for facilitating adaptive learning for diverse learners at scale, it could disproportionately neglect older cohorts and other digitally marginalized populations, with most benefits accruing to younger generations instead. In this paper, we examine how analytics can utilize AI to model digital literacy and learning requirements using PIAAC microdata from Turkey. Methods: Feature sets with diverse variables were constructed, including indicators for technology-based problem solving, plausible values for literacy and numeracy, indices related to technology utilization and accessibility, demographic factors, and engagement and motivation indicators. After weight-aware preprocessing, supervised machine learning models—Random Forest classifier, Gradient Boosting classifier, Support Vector Machine classifier, and Multi-Layer Perceptron classifier—were applied to predict continuous digital competence scores and to classify high/low digital competence. SHAP analysis was used to interpret the machine learning models. Learner profiles were established using UMAP and k-means clustering techniques. Results: Gradient Boosting and Random Forest models demonstrate the best compromise between discrimination power and calibration of predicted probabilities. Literacy, numeracy, engagement with digital technologies, and motivational variables emerge as dominant factors, while a strong negative age gradient suggests intergenerational disparities. Three distinct learner types—low-, moderate-, and high-level learners—differ significantly across clusters, defining distinct patterns of learning needs. Conclusion: The findings suggest that AI-supported lifelong learning systems need to link skill-building with motivational components and continuous fairness 1tracking. Human-centered AI design is required to avoid compounding inequalities and to guarantee equitable access to innovative digital learning tools for older adults and other at-risk populations. lifelong learning artificial intelligence digital competence personalized learning systems adaptive learning educational data mining AI ethics in education model interpretability subgroup fairness intelligent tutoring systems Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 07 Jan, 2026 Reviews received at journal 05 Jan, 2026 Reviewers agreed at journal 14 Dec, 2025 Reviews received at journal 11 Dec, 2025 Reviewers agreed at journal 10 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviewers invited by journal 09 Dec, 2025 Editor assigned by journal 01 Dec, 2025 Submission checks completed at journal 01 Dec, 2025 First submitted to journal 29 Nov, 2025 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-8238956","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":558605103,"identity":"09bbf167-78ed-4e01-b3db-04fa6392fbb3","order_by":0,"name":"Nihan OZBALTAN","email":"data:image/png;base64,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","orcid":"","institution":"Bakırçay Üniversitesi","correspondingAuthor":true,"prefix":"","firstName":"Nihan","middleName":"","lastName":"OZBALTAN","suffix":""}],"badges":[],"createdAt":"2025-11-29 19:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8238956/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8238956/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98009490,"identity":"4f3e24f6-980a-4dc2-a740-a836559cfeb0","added_by":"auto","created_at":"2025-12-11 18:05:40","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3962,"visible":true,"origin":"","legend":"","description":"","filename":"f473a5282783444697a0acb31d595eec.json","url":"https://assets-eu.researchsquare.com/files/rs-8238956/v1/c6721fa1c50d1380e381e51d.json"},{"id":98426018,"identity":"ebde6063-f521-444c-9af5-803112a37853","added_by":"auto","created_at":"2025-12-17 16:35:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1025629,"visible":true,"origin":"","legend":"","description":"","filename":"aiinedu.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8238956/v1_covered_5df2a865-1f1c-45a8-8f70-30722073673a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI-Supported Lifelong Learning: Predicting Digital Competence and Learner Profiles with PIAAC Turkey Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"humancentric-intelligent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Human-Centric Intelligent Systems](https://link.springer.com/journal/44230)","snPcode":"44230","submissionUrl":"https://submission.springernature.com/new-submission/44230/3","title":"Human-Centric Intelligent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"lifelong learning, artificial intelligence, digital competence, personalized learning systems, adaptive learning, educational data mining, AI ethics in education, model interpretability, subgroup fairness, intelligent tutoring systems","lastPublishedDoi":"10.21203/rs.3.rs-8238956/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8238956/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePurpose:\u003c/strong\u003e Although AI offers enormous potential for facilitating adaptive learning for diverse learners at scale, it could disproportionately neglect older cohorts and other digitally marginalized populations, with most benefits accruing to younger generations instead. In this paper, we examine how analytics can utilize AI to model digital literacy and learning requirements using PIAAC microdata\u0026nbsp;from Turkey.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eFeature sets with diverse variables were constructed, including indicators for technology-based problem solving, plausible values for literacy and\u0026nbsp;numeracy, indices related to technology utilization and accessibility, demographic factors, and engagement and motivation indicators. After weight-aware preprocessing, supervised machine learning models—Random Forest classifier, Gradient Boosting classifier, Support Vector Machine classifier, and Multi-Layer Perceptron classifier—were applied to predict continuous digital competence scores and to classify high/low digital competence. SHAP analysis was used to interpret the machine learning models. Learner profiles were established using UMAP and k-means clustering techniques.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Gradient Boosting and Random Forest models demonstrate the best compromise between discrimination power and calibration of predicted probabilities. Literacy, numeracy, engagement with digital technologies, and motivational variables emerge as dominant factors, while a strong negative age gradient suggests intergenerational disparities. Three distinct learner types—low-, moderate-, and high-level learners—differ significantly across clusters, defining distinct patterns of learning needs.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion: \u003c/strong\u003eThe findings suggest that AI-supported lifelong learning systems need to link skill-building with motivational components and continuous fairness 1tracking. Human-centered AI design is required to avoid compounding inequalities and to guarantee equitable access to innovative digital learning tools for older adults and other at-risk populations.\u003c/p\u003e","manuscriptTitle":"AI-Supported Lifelong Learning: Predicting Digital Competence and Learner Profiles with PIAAC Turkey Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-11 18:05:33","doi":"10.21203/rs.3.rs-8238956/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-07T07:59:44+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-06T02:48:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"241026078595917996239826264182350236525","date":"2025-12-14T13:21:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-11T05:59:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"93320305885585330078041633406070581664","date":"2025-12-10T13:55:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59611013213652889175014508370905160009","date":"2025-12-09T08:47:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-09T08:26:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-02T03:47:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-01T23:45:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Human-Centric Intelligent Systems","date":"2025-11-29T19:31:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"humancentric-intelligent-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Human-Centric Intelligent Systems](https://link.springer.com/journal/44230)","snPcode":"44230","submissionUrl":"https://submission.springernature.com/new-submission/44230/3","title":"Human-Centric Intelligent Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b1aa4e51-c21d-45c1-a8ad-e6fa786d4576","owner":[],"postedDate":"December 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-03-16T14:27:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-11 18:05:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8238956","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8238956","identity":"rs-8238956","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}