Fake Review Detection and Text Analysis by Using Clustering Techniques on LSTM

Fake Review Detection and Text Analysis by Using Clustering Techniques on LSTM | 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Detection and Text Analysis by Using Clustering Techniques on LSTM Tianle Dai, Xiaodong Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4533037/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 growth of the internet, the issue of fake reviews has become increasingly prominent. Traditional models for fake review detection have underperformed on balanced datasets, leading to difficulties in differentiating between the genuine and the fake reviews. This paper introduces a model based on k-Means text clustering neural networks. Firstly, the genuine review texts are vectorized after stop-word removal using TF-IDF to determine the weights of each word and map them into a high-dimensional space. Then, the k-Means clustering algorithm is employed to cluster these reviews in the space. From each cluster center, the genuine reviews equal in number to the fake reviews are extracted. By analyzing keywords from different clusters, the model learns the linguistic behaviors distinguishing the genuine reviewers from the fake ones. These reviews are then processed by a Long Short-Term Memory (LSTM) network to extract and analyze their features. Finally, prediction outcomes are produced. Experimental results on the Yelp dataset demonstrate that the text clustering neural network model outperforms existing models, showcasing enhanced performance. K-Means Clustering LSTM Fake Review Detection Text Feature Extraction. 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-4533037","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":314808092,"identity":"10ad5d56-bfdc-4064-be7e-c58803c37108","order_by":0,"name":"Tianle Dai","email":"","orcid":"","institution":"Mudanjiang Normal University","correspondingAuthor":false,"prefix":"","firstName":"Tianle","middleName":"","lastName":"Dai","suffix":""},{"id":314808096,"identity":"b496adce-bd5c-4efa-beaf-0b8a43922cba","order_by":1,"name":"Xiaodong Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYNACAyA+AMQfGJiZwQI8xGphnEG8FgaIFmYeBogOvFoMjp89/JqnwE6O73jv4de2Odbs5hIJjA/etjHIm+PSciYvzXKGQbKx5Jlzada529KZLWckMBvObWMw3NmAXYvZgRwzgw8GzIkbbuSYGeduO8xscCOBTZq3jSHB4AAOLeffmBkkGNRDtFhCtLD/xqvlRo7xgw8Gh0FajB8zQm1hxqfF/sYbM8YZBseBfjljxtgL9IvBmYfNknPOSRhuwKFFsj/H+DPPn2pgiPUYf/i5zTrZ4HjywQ9vymzkcdkCBGwSyIxkYIw2AGkJnOqBgPkDMsMOn9JRMApGwSgYmQAA2GVeAVMaVpQAAAAASUVORK5CYII=","orcid":"","institution":"Mudanjiang Normal University","correspondingAuthor":true,"prefix":"","firstName":"Xiaodong","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-06-05 09:42:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4533037/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4533037/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64228291,"identity":"2b815168-6f6d-4253-a503-bb6e3ab84a14","added_by":"auto","created_at":"2024-09-10 14:21:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":512600,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4533037/v1_covered_8a3ab373-2301-43b5-a4a7-228fcb545bba.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fake Review Detection and Text Analysis by Using Clustering Techniques on LSTM","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":"K-Means Clustering, LSTM, Fake Review Detection, Text Feature Extraction.","lastPublishedDoi":"10.21203/rs.3.rs-4533037/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4533037/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWith the growth of the internet, the issue of fake reviews has become increasingly prominent. Traditional models for fake review detection have underperformed on balanced datasets, leading to difficulties in differentiating between the genuine and the fake reviews. This paper introduces a model based on k-Means text clustering neural networks. Firstly, the genuine review texts are vectorized after stop-word removal using TF-IDF to determine the weights of each word and map them into a high-dimensional space. Then, the k-Means clustering algorithm is employed to cluster these reviews in the space. From each cluster center, the genuine reviews equal in number to the fake reviews are extracted. By analyzing keywords from different clusters, the model learns the linguistic behaviors distinguishing the genuine reviewers from the fake ones. These reviews are then processed by a Long Short-Term Memory (LSTM) network to extract and analyze their features. Finally, prediction outcomes are produced. Experimental results on the Yelp dataset demonstrate that the text clustering neural network model outperforms existing models, showcasing enhanced performance.\u003c/p\u003e","manuscriptTitle":"Fake Review Detection and Text Analysis by Using Clustering Techniques on LSTM","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-21 03:10:37","doi":"10.21203/rs.3.rs-4533037/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":"a3c9f09e-72e4-4c85-9662-dfd894fa3f5a","owner":[],"postedDate":"June 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-09-10T14:12:56+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-21 03:10:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4533037","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4533037","identity":"rs-4533037","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}