A Multi-Layer Framework for Detecting Fake Reviews and Improving App Rating Integrity

A Multi-Layer Framework for Detecting Fake Reviews and Improving App Rating Integrity | 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 A Multi-Layer Framework for Detecting Fake Reviews and Improving App Rating Integrity Herve Dimitri Motsakou Gandze, Yangyu Hu, Lilian Chiru Kawala This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6995969/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 User ratings and reviews are essential for app recommendations but are increasingly undermined by fake and manipulated feedback. This paper presents RCAR (Rating-Corrected App Recommendation), a multi-layer framework designed to detect review fraud and improve rating accuracy. RCAR combines sentiment–rating alignment, comment similarity, graph-based tie strength, and community detection to assess reviewer credibility and correct app scores. Evaluated on over 100,000 reviews, RCAR achieves an AUC-PR of 0.94 in identifying genuine reviewers and reduces fake review influence by 40%. It also improves rating accuracy, notably increasing LINE’s score from 2.15 to 3.35 and decreasing VK Video’s from 2.64 to 1.44. These results demonstrate RCAR’s effectiveness in enhancing app store transparency and recommendation quality. Fake review detection Graph-based clustering Behavioral analytics Rating correction 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-6995969","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":481815350,"identity":"a46e381e-a804-4bac-812d-6b9f87e2c737","order_by":0,"name":"Herve Dimitri Motsakou Gandze","email":"","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Herve","middleName":"Dimitri Motsakou","lastName":"Gandze","suffix":""},{"id":481815351,"identity":"2eec4073-2ad6-4d4e-8ddd-416db3f24641","order_by":1,"name":"Yangyu Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYBACAxiDHy50gFgtkg0gMoEULQYHiNViLpFj+Lng1+HEzccPb5Mu/MEgx3cjgfFzAR4tljNyjKVn9h1O3HYmrUx6RgKDseSNBGbpGfgcdiPHQJq3B6jlBo+ZNE8CQ+KGGwlszDz4tRj/BmnZPAOipZ4YLUCVPw4nbpCAaEkwIKjlzLMya96GdOMZZ9KKrWekSRjOPPOwWRqvluPJm2/z/LGW7W8/vPF2gY2NPN/x5IOf8WlhYOAwYGBsawZrZ2ZgkADSjA14NTAwsD9gYPhTB9MyCkbBKBgFowATAACWu02Id/sCWQAAAABJRU5ErkJggg==","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Yangyu","middleName":"","lastName":"Hu","suffix":""},{"id":481815352,"identity":"10101058-b058-42fa-a580-280c595f5c84","order_by":2,"name":"Lilian Chiru Kawala","email":"","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Lilian","middleName":"Chiru","lastName":"Kawala","suffix":""}],"badges":[],"createdAt":"2025-06-28 06:53:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6995969/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6995969/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91787531,"identity":"25d0ab21-35ef-4a06-bec2-2e1b169cf3c6","added_by":"auto","created_at":"2025-09-21 09:23:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1633764,"visible":true,"origin":"","legend":"","description":"","filename":"CombatingFakeReviews.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6995969/v1_covered_6eb5d24f-dc62-470f-9527-fe54d5ae0ad7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multi-Layer Framework for Detecting Fake Reviews and Improving App Rating Integrity","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":"Fake review detection, Graph-based clustering, Behavioral analytics, Rating correction","lastPublishedDoi":"10.21203/rs.3.rs-6995969/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6995969/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eUser ratings and reviews are essential for app recommendations but are increasingly undermined by fake and manipulated feedback. This paper presents RCAR (Rating-Corrected App Recommendation), a multi-layer framework designed to detect review fraud and improve rating accuracy. RCAR combines sentiment\u0026ndash;rating alignment, comment similarity, graph-based tie strength, and community detection to assess reviewer credibility and correct app scores. Evaluated on over 100,000 reviews, RCAR achieves an AUC-PR of 0.94 in identifying genuine reviewers and reduces fake review influence by 40%. It also improves rating accuracy, notably increasing LINE\u0026rsquo;s score from 2.15 to 3.35 and decreasing VK Video\u0026rsquo;s from 2.64 to 1.44. These results demonstrate RCAR\u0026rsquo;s effectiveness in enhancing app store transparency and recommendation quality.\u003c/p\u003e","manuscriptTitle":"A Multi-Layer Framework for Detecting Fake Reviews and Improving App Rating Integrity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-11 08:22:34","doi":"10.21203/rs.3.rs-6995969/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":"6358db02-2c15-4b3c-9c33-86297f97c28e","owner":[],"postedDate":"July 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-21T09:23:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-11 08:22:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6995969","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6995969","identity":"rs-6995969","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}