Multi-Label Machine Learning Models for Trolling and Cyberbullying Prediction

Multi-Label Machine Learning Models for Trolling and Cyberbullying Prediction | 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 Multi-Label Machine Learning Models for Trolling and Cyberbullying Prediction Adenrele A. Afolorunso, Oluwasogo A. Okunade, Morufu Olalere, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7622077/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 With the popularity of social media, online trolling and cyberbullying remain persistent and well-spread challenges to netizens, with considerable harms to human well-being and community cohesion. This study develops a multi-label machine learning framework for automated prediction of trolling and bullying in the cyberspace using a publicly available Kaggle dataset (cyberbullying_dataset_CSV_version.csv) comprising 280,050 comments annotated with 81 nonmutuallyexclusive categories. The corpus is genuinely multi-labelled (mean 1.99 labels per comment), with the most frequent categories including religious hate, political hate, other cyberbullying types, ethnic hate, threats, and trolling. Classical (LogReg, SVM, RF), sequence (BiLSTM), and transformer-based (BERT) models are benchmarked under a consistent pipeline that (i) learns per-label decision thresholds on a validation split, and (ii) evaluates with metrics suited to multi-label settings (Micro/Macro-F1, Hamming Loss, Subset Accuracy). Experimental results show that fine-tuned BERT achieves the strongest overall performance, improving over BiLSTM by +0.06 Micro-F1 (from 0.81 to 0.87), +0.08 Macro-F1 (0.70 to 0.78), and +0.09 Subset Accuracy (0.52 to 0.61), while reducing Hamming Loss by-0.015 (0.067 to 0.052). We provide model architectures, implementation details, and rich visual diagnostics (grouped bars with uncertainty, multi-metric radar, label-wise heatmap), and we discuss thresholding, calibration, and fairness. The results obtained and practices support reproducible research and reliable deployment of multi-label moderation systems trained on Kaggle-scale data. Multi-label classification Trolling prediction Cyberbullying NLP BERT Fairness Full Text 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-7622077","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":535932590,"identity":"f786e796-c0dd-4e33-8ce4-33f8b143be48","order_by":0,"name":"Adenrele A. Afolorunso","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYFACxgcMD8AMHgaGD1AxCfxamA0YEqBaGGeQrIWZhxgt/O2HGR8kVNxL3M5/9uBj2x02idsZmA/e5mG4Y9eAQ4vEmWRmg4QzxYk7Z+QlG+eeSUvc2cCWbM3D8CwZlxaGA/nHJBLbEhI33OAxk85tO5y44QCQwcNwOBmXDvnzj9kgWs6fMZO2BGvh/4ZXi8GNZKiWAzlm0owQW9hAWuxwaTG88RjklwTjDTdyjA1729KMNxxmM7acY3A4AZcWufPJjA8+VCTIAh1m+OBnm43shuPND2+8qThsj0sLFsAMdjBDYgMJeiCAFFtGwSgYBaNgeAMArwVaKhGoYJwAAAAASUVORK5CYII=","orcid":"","institution":"National Open University of Nigeria","correspondingAuthor":true,"prefix":"","firstName":"Adenrele","middleName":"A.","lastName":"Afolorunso","suffix":""},{"id":535932591,"identity":"a8206a79-7cee-4069-b10c-a5a862cfe1a0","order_by":1,"name":"Oluwasogo A. Okunade","email":"","orcid":"","institution":"National Open University of Nigeria","correspondingAuthor":false,"prefix":"","firstName":"Oluwasogo","middleName":"A.","lastName":"Okunade","suffix":""},{"id":535932592,"identity":"a42aa558-eb84-4564-9b2e-a8e98dc672db","order_by":2,"name":"Morufu Olalere","email":"","orcid":"","institution":"National Open University of Nigeria","correspondingAuthor":false,"prefix":"","firstName":"Morufu","middleName":"","lastName":"Olalere","suffix":""},{"id":535932593,"identity":"c414d138-efb3-4d5e-bfcb-3228eebafdd1","order_by":3,"name":"Adeyinka O. Abiodun","email":"","orcid":"","institution":"National Open University of Nigeria","correspondingAuthor":false,"prefix":"","firstName":"Adeyinka","middleName":"O.","lastName":"Abiodun","suffix":""},{"id":535932594,"identity":"4fa37e44-94d9-4a7a-a301-716ca697f38e","order_by":4,"name":"Olawale Surajudeen Adebayo","email":"","orcid":"","institution":"National Open University of Nigeria","correspondingAuthor":false,"prefix":"","firstName":"Olawale","middleName":"Surajudeen","lastName":"Adebayo","suffix":""}],"badges":[],"createdAt":"2025-09-15 15:08:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7622077/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7622077/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94670339,"identity":"cd8cbb0e-1d0a-4783-9ee6-c33ee8a25fd4","added_by":"auto","created_at":"2025-10-29 13:09:12","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":279237,"visible":true,"origin":"","legend":"","description":"","filename":"MachineLearningModelBasedTrollingandCyberbullyingPredictionMultiLabelModelingwithArchitectureandImplementation4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7622077/v1/727bd5ebeb4df55d5fad151e.pdf"},{"id":94670338,"identity":"ad693258-2a89-461a-bb15-9fd6e065f162","added_by":"auto","created_at":"2025-10-29 13:09:12","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7402,"visible":true,"origin":"","legend":"","description":"","filename":"3490ab4277884625bc31fd67d981564a.json","url":"https://assets-eu.researchsquare.com/files/rs-7622077/v1/1f9c349742b6130611fc0ba8.json"},{"id":100235514,"identity":"fd9a57e4-9e0f-4ca4-842a-70e73af16a1c","added_by":"auto","created_at":"2026-01-14 12:25:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":259222,"visible":true,"origin":"","legend":"","description":"","filename":"MachineLearningModelBasedTrollingandCyberbullyingPredictionMultiLabelModelingwithArchitectureandImplementation4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7622077/v1_covered_43b65efc-8d79-4232-892a-cfe8a414608b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Label Machine Learning Models for Trolling and Cyberbullying Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Multi-label classification, Trolling prediction, Cyberbullying, NLP, BERT, Fairness","lastPublishedDoi":"10.21203/rs.3.rs-7622077/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7622077/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the popularity of social media, online trolling and cyberbullying remain persistent and well-spread challenges to netizens, with considerable harms to human well-being and community cohesion. This study develops a multi-label machine learning framework for automated prediction of trolling and bullying in the cyberspace using a publicly available Kaggle dataset (cyberbullying_dataset_CSV_version.csv) comprising 280,050 comments annotated with 81 nonmutuallyexclusive categories. The corpus is genuinely multi-labelled (mean 1.99 labels per comment), with the most frequent categories including religious hate, political hate, other cyberbullying types, ethnic hate, threats, and trolling. Classical (LogReg, SVM, RF), sequence (BiLSTM), and transformer-based (BERT) models are benchmarked under a consistent pipeline that (i) learns per-label decision thresholds on a validation split, and (ii) evaluates with metrics suited to multi-label settings (Micro/Macro-F1, Hamming Loss, Subset Accuracy). Experimental results show that fine-tuned BERT achieves the strongest overall performance, improving over BiLSTM by +0.06 Micro-F1 (from 0.81 to 0.87), +0.08 Macro-F1 (0.70 to 0.78), and +0.09 Subset Accuracy (0.52 to 0.61), while reducing Hamming Loss by-0.015 (0.067 to 0.052). We provide model architectures, implementation details, and rich visual diagnostics (grouped bars with uncertainty, multi-metric radar, label-wise heatmap), and we discuss thresholding, calibration, and fairness. The results obtained and practices support reproducible research and reliable deployment of multi-label moderation systems trained on Kaggle-scale data.","manuscriptTitle":"Multi-Label Machine Learning Models for Trolling and Cyberbullying Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-29 13:08:58","doi":"10.21203/rs.3.rs-7622077/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":"0a27cc2e-aba0-4fb1-bf08-654b28695992","owner":[],"postedDate":"October 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-14T12:25:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-29 13:08:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7622077","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7622077","identity":"rs-7622077","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}