Detecting Flagged Comments by Analyzing User Behavior Features in Online Communities

Detecting Flagged Comments by Analyzing User Behavior Features in Online Communities | 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 Article Detecting Flagged Comments by Analyzing User Behavior Features in Online Communities Juan Tang, Xun Tang, Binbin Ning, Kanghong Ma, Linli Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6617792/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 Comments violating community guidelines have long been a challenge in online discussion communities, often disrupting the user experience and overall community health. This study provides a quantitative analysis of such flagged comments within a large online Chinese discussion platform, examining factors like comment deletion rates, sentiment, discussion context influence, user voting behavior, and timing of comment publication. Our dataset comprises 6,900,119 historical comments from 17,226 users, collected and meticulously cleaned for analysis. Feature analysis reveals that users with higher comment deletion rates are more prone to trolling behavior. Additionally, flagged first or root comments are found to increase the likelihood of subsequent flagged comments within a discussion. Flagged comments also tend to attract more negative votes and appear earlier in the discussion. Leveraging these behavioral features, we built a high-accuracy predictive model that achieved an AUC of 99.2% in identifying flagged comments. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Scientific data Physical sciences/Mathematics and computing/Statistics Misbehavior Community Flagged comments Machine learning 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-6617792","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":463873495,"identity":"cdc46e0e-af23-4591-b5f1-6a8ea7e60c03","order_by":0,"name":"Juan Tang","email":"","orcid":"","institution":"Sichuan Jiuzhou Electric Group Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"","lastName":"Tang","suffix":""},{"id":463873496,"identity":"9e5d80c2-6858-4072-9eca-2a37e63b7f74","order_by":1,"name":"Xun Tang","email":"","orcid":"","institution":"Chengdu Shentuo Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Xun","middleName":"","lastName":"Tang","suffix":""},{"id":463873497,"identity":"ff9b3f3a-589b-4a26-b20a-b44aca34697a","order_by":2,"name":"Binbin Ning","email":"","orcid":"","institution":"Sichuan Jiuzhou Electric Group Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Binbin","middleName":"","lastName":"Ning","suffix":""},{"id":463873498,"identity":"1ea0cf90-8aa4-4f3c-ab21-ae8150b401ff","order_by":3,"name":"Kanghong Ma","email":"","orcid":"","institution":"Sichuan Jiuzhou Electric Group Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Kanghong","middleName":"","lastName":"Ma","suffix":""},{"id":463873499,"identity":"50aac88e-238d-4222-9e16-f82305b79ec6","order_by":4,"name":"Linli Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIie3QsQrCMBCA4QuB6BDMJikOfYUTlw4+TNw7dHTSSFfFNcWX6CNEDjrpE7gIvkDBpaOdRWi6OeSf74O7A4jF/rAZ59ZDofdnVXrfdgFEcNYT1KxyzeZaHUMIMAuAwGqfr2gqQsiEHajAjCf21hJISNXcDy9GDrVQ/FRTkcGyupgAIlHLxN5rchIMPgKJRp8/SYoRBHsC44hJXIP9k/XwLUoRveV2Z5QqX23brVO1GCDf6XHjsVgsFvvdB9K1QWnpDi9uAAAAAElFTkSuQmCC","orcid":"","institution":"Sichuan Jiuzhou Electric Group Co., Ltd","correspondingAuthor":true,"prefix":"","firstName":"Linli","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-05-08 07:23:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6617792/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6617792/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84274967,"identity":"5362e4c3-9317-4cf8-9a9d-7b2f08ce616e","added_by":"auto","created_at":"2025-06-10 05:31:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":606210,"visible":true,"origin":"","legend":"","description":"","filename":"DetectingFlaggedCommentsbyAnalyzingUserBehaviorFeaturesinOnlineCommunities.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6617792/v1_covered_9a94a9ae-5282-453a-bbfb-2236720539c9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Detecting Flagged Comments by Analyzing User Behavior Features in Online Communities","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":"Misbehavior, Community, Flagged comments, Machine learning","lastPublishedDoi":"10.21203/rs.3.rs-6617792/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6617792/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e Comments violating community guidelines have long been a challenge in online discussion communities, often disrupting the user experience and overall community health. This study provides a quantitative analysis of such flagged comments within a large online Chinese discussion platform, examining factors like comment deletion rates, sentiment, discussion context influence, user voting behavior, and timing of comment publication. Our dataset comprises 6,900,119 historical comments from 17,226 users, collected and meticulously cleaned for analysis. Feature analysis reveals that users with higher comment deletion rates are more prone to trolling behavior. Additionally, flagged first or root comments are found to increase the likelihood of subsequent flagged comments within a discussion. Flagged comments also tend to attract more negative votes and appear earlier in the discussion. Leveraging these behavioral features, we built a high-accuracy predictive model that achieved an AUC of 99.2% in identifying flagged comments.\u003c/p\u003e","manuscriptTitle":"Detecting Flagged Comments by Analyzing User Behavior Features in Online Communities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-30 13:31:23","doi":"10.21203/rs.3.rs-6617792/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":"9fb42d15-7727-4be1-bb11-bba3ab41c9cf","owner":[],"postedDate":"May 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49256209,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":49256210,"name":"Physical sciences/Mathematics and computing/Scientific data"},{"id":49256211,"name":"Physical sciences/Mathematics and computing/Statistics"}],"tags":[],"updatedAt":"2025-06-10T05:23:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-30 13:31:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6617792","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6617792","identity":"rs-6617792","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}