Fake Review Detection in Yelp Restaurant Reviews via Natural Language Processing

Fake Review Detection in Yelp Restaurant Reviews via Natural Language Processing | 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 Fake Review Detection in Yelp Restaurant Reviews via Natural Language Processing Shenil Polpolage This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6305783/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 Fake reviews are becoming a greater problem for online platforms, especially in the restaurant world. These dodgy reviews can hurt businesses; smaller ones often pinch the most because they mess with people’s trust and sway their buying decisions. Traditional ways of sniffing out fake reviews, such as manually going through them, are relatively slow and not very reliable; however, they are effective only approximately 57% of the time. However, that is where machine learning comes in with natural language processing. It is a game changer that uses enormous datasets and smart algorithms to find those tells that give away fake reviews via sentiment analysis. By looking at how people write, things such as grammar and meaning, and how they behave, such as how engaged they are or when they post, machine learning can do way better than the previous methods can. This study is all about pushing for better fake review detection systems that can help both businesses and customers, hitting accuracy rates of over 95% via behavioral feature extraction. Theoretical Computer Science Fake review Machine learning Natural language processing Sentiment analysis Behavioral feature extraction Full Text Additional Declarations The authors declare no competing interests. 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-6305783","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":433889382,"identity":"7f169afa-964c-4100-b92f-0783a2d50278","order_by":0,"name":"Shenil Polpolage","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYDACZuYDBxIMJOrZ2BuAvAIGGQmCWtjZEh98qLBJ4OM5AOQZMPAQ1sLPo2w440xagpxEApFa5Jt52KR52w7nsUk+Pib5A6hFsoGAFoPDvMdAWorZpNPSpHmAWqQJ2WLAzJcG0sLYJp1jJg1ymBwRDjODaJE8YwZ2GEEtDId5jEHeT2yT4DGTIM5hhyGBbMzGk5ZszWMgQdj78v2HwVEpJ99++ODNHxU2chIHCLoMFRCOyFEwCkbBKBgFRAAA9BE0uJuaTRgAAAAASUVORK5CYII=","orcid":"","institution":"The Open university Sri Lanka","correspondingAuthor":true,"prefix":"","firstName":"Shenil","middleName":"","lastName":"Polpolage","suffix":""}],"badges":[],"createdAt":"2025-03-25 16:48:27","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6305783/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6305783/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79235906,"identity":"5f8ca2c0-1dd3-438b-b7ed-009000fbe73f","added_by":"auto","created_at":"2025-03-26 04:08:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":291567,"visible":true,"origin":"","legend":"","description":"","filename":"FakeReviewAnalysisFinalVersion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6305783/v1_covered_1a5243ca-77fb-49fe-9d4c-9dbe0b148d41.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eFake Review Detection in Yelp Restaurant Reviews via Natural Language Processing\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"The Open University Sri Lanka","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, Machine learning, Natural language processing, Sentiment analysis, Behavioral feature extraction","lastPublishedDoi":"10.21203/rs.3.rs-6305783/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6305783/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFake reviews are becoming a greater problem for online platforms, especially in the restaurant world. These dodgy reviews can hurt businesses; smaller ones often pinch the most because they mess with people’s trust and sway their buying decisions. Traditional ways of sniffing out fake reviews, such as manually going through them, are relatively slow and not very reliable; however, they are effective only approximately 57% of the time. However, that is where machine learning comes in with natural language processing. It is a game changer that uses enormous datasets and smart algorithms to find those tells that give away fake reviews via sentiment analysis. By looking at how people write, things such as grammar and meaning, and how they behave, such as how engaged they are or when they post, machine learning can do way better than the previous methods can. This study is all about pushing for better fake review detection systems that can help both businesses and customers, hitting accuracy rates of over 95% via behavioral feature extraction.\u003c/p\u003e","manuscriptTitle":"Fake Review Detection in Yelp Restaurant Reviews via Natural Language Processing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-26 04:00:05","doi":"10.21203/rs.3.rs-6305783/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":"d31fc1cf-ba12-4ac4-ac7f-c253b29452e2","owner":[],"postedDate":"March 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46201865,"name":"Theoretical Computer Science"}],"tags":[],"updatedAt":"2025-03-26T04:00:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-26 04:00:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6305783","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6305783","identity":"rs-6305783","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}