Comparison of Algorithms for the Recognition of ChatGPT Paraphrased Texts

Comparison of Algorithms for the Recognition of ChatGPT Paraphrased Texts | 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 Comparison of Algorithms for the Recognition of ChatGPT Paraphrased Texts Aleksandar Kartelj, Miljana Mladenovic, Stasa Vujicic Stankovic This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5107971/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 The rapid development of artificial intelligence, especially chatbots, is leading to new forms of plagiarism that are difficult to detect using existing methods. Paraphrasing tools make this problem even more difficult and are incredible in minor languages with inadequate resources and tools. This study explores strategies that can help detect plagiarism generated by ChatGPT 4.0 and altered by paraphrasing tools. We propose two new datasets consisting of abstracts of doctoral theses in English and Serbian. Both datasets were subjected to ChatGPT paraphrasing, which allowed us to form two classes of texts: human-generated and AI-generated, i.e. AI-paraphrased. We then perform a comprehensive comparison of 19 widely used classification algorithms based on two feature sets, namely word unigrams and character multigrams. In addition, we compare these to the results of a commercially available pre-trained ChatGPT content detector, ZeroGPT. The results on the English corpus turn out to be very accurate, achieving an accuracy of 95% or more. In contrast, the results on the Serbian corpus were less accurate, achieving an accuracy of just over 85%. We attribute this difference to the lower ability of ChatGPT to parahprase in minor languages such as Serbian. Artificial Intelligence and Machine Learning Plagiarism Detection ChatGPT Classification Large Language Models 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-5107971","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":355607732,"identity":"c30ec1f6-995d-427f-82e5-e74b1c44bb5b","order_by":0,"name":"Aleksandar Kartelj","email":"","orcid":"https://orcid.org/0000-0001-9839-6039","institution":"University of Belgrade, Faculty of Mathematics","correspondingAuthor":false,"prefix":"","firstName":"Aleksandar","middleName":"","lastName":"Kartelj","suffix":""},{"id":355607733,"identity":"91eca277-cfa0-456c-a31b-62279d93440c","order_by":1,"name":"Miljana Mladenovic","email":"","orcid":"https://orcid.org/0000-0002-7973-452X","institution":"University of Nis, Faculty of Education","correspondingAuthor":false,"prefix":"","firstName":"Miljana","middleName":"","lastName":"Mladenovic","suffix":""},{"id":355607734,"identity":"12383157-ba05-4d09-b314-b4a731dd7526","order_by":2,"name":"Stasa Vujicic Stankovic","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-7200-3724","institution":"University of Belgrade, Faculty of Mathematics","correspondingAuthor":true,"prefix":"","firstName":"Stasa","middleName":"Vujicic","lastName":"Stankovic","suffix":""}],"badges":[],"createdAt":"2024-09-18 07:51:36","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-5107971/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5107971/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64879243,"identity":"1610b99f-d39c-4950-a83f-69cfbdbac9d9","added_by":"auto","created_at":"2024-09-20 02:48:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":981600,"visible":true,"origin":"","legend":"","description":"","filename":"ComparisonofAlgorithmsfortheRecognitionofChatGPTParaphrasedTexts.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5107971/v1_covered_bef5cd25-2d2c-41b3-80ec-6830e3fd09b3.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparison of Algorithms for the Recognition of ChatGPT Paraphrased Texts\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Plagiarism Detection, ChatGPT, Classification, Large Language Models","lastPublishedDoi":"10.21203/rs.3.rs-5107971/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5107971/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid development of artificial intelligence, especially chatbots, is leading to new forms of plagiarism that are difficult to detect using existing methods. Paraphrasing tools make this problem even more difficult and are incredible in minor languages with inadequate resources and tools. This study explores strategies that can help detect plagiarism generated by ChatGPT 4.0 and altered by paraphrasing tools. We propose two new datasets consisting of abstracts of doctoral theses in English and Serbian. Both datasets were subjected to ChatGPT paraphrasing, which allowed us to form two classes of texts: human-generated and AI-generated, i.e. AI-paraphrased. We then perform a comprehensive comparison of 19 widely used classification algorithms based on two feature sets, namely word unigrams and character multigrams. In addition, we compare these to the results of a commercially available pre-trained ChatGPT content detector, ZeroGPT. The results on the English corpus turn out to be very accurate, achieving an accuracy of 95% or more. In contrast, the results on the Serbian corpus were less accurate, achieving an accuracy of just over 85%. We attribute this difference to the lower ability of ChatGPT to parahprase in minor languages such as Serbian.\u003c/p\u003e","manuscriptTitle":"Comparison of Algorithms for the Recognition of ChatGPT Paraphrased Texts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-20 02:39:59","doi":"10.21203/rs.3.rs-5107971/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":"2f5153e9-762a-414b-85fc-f39730405d4b","owner":[],"postedDate":"September 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":37922293,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-09-20T02:39:59+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-20 02:39:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5107971","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5107971","identity":"rs-5107971","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}