Discerning Human and AI-Generated Content in Short- Form Text | 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 Discerning Human and AI-Generated Content in Short- Form Text Somesh Jadhwani, Shreya Jain, Pankti Doshi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5870405/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract With the exponential rise in AI-powered language models, distinguishing human-generated text from AI-generated content has become increasingly vital for combating misinformation and maintaining trust on online platforms. This study explores the unique challenge of identifying whether casual, short-form user reviews on e-commerce websites are authored by humans or generated by AI. A comprehensive dataset comprising over 60,000 genuine reviews and 17,645 AI-generated reviews, spanning various product categories, was created through web scraping and the use of advanced language models. Leveraging robust feature engineering, model development, and statistical analysis, this research demonstrates the potential to reliably classify human and AI-generated content in informal, short-form contexts. Generative Artificial Intelligence LLM ChatGPT Scraping Fake Reviews Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 24 Jan, 2025 Submission checks completed at journal 24 Jan, 2025 First submitted to journal 21 Jan, 2025 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-5870405","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":406905518,"identity":"7bc178ae-496b-4dbc-9812-30ff78ff18b7","order_by":0,"name":"Somesh Jadhwani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIie3RsUrEMBgH8K8Eektr1pSqfYUchdPhsK/ScuDUgk8gBSEd5HZfQ4TejQdCXXJ7pIPo4HQKLkI4Bb+Am229UTD/KST5kX8SABubvxqnBAKQmyHzXLhdAXAckx3JPnWadCcC3wSmwYXkg52i6jJ71EsY0apomF4ee7yR70/qrE5g5K+6CJfrm9iXQJh8PQ3mknk4s4hz3mYl2Us7CSvq0BHYW+UT5Qskal2HSFIgXmfD6KpYaI0kQnL/acjD5tmQpI+AKmrwkXAkrTklKKVriFP2EHOXEHeSsdwcbQ+QUGgmhmSir1g1v37TYjo7vMvj8Ys4T/ArsdhHm1A6+Nps9nPOHdhvcvLLuo2Njc1/zhfo6F5GHwLZtAAAAABJRU5ErkJggg==","orcid":"","institution":"NMIMS University","correspondingAuthor":true,"prefix":"","firstName":"Somesh","middleName":"","lastName":"Jadhwani","suffix":""},{"id":406905519,"identity":"337b3e00-dba6-422e-a212-5e6e35c9458f","order_by":1,"name":"Shreya Jain","email":"","orcid":"","institution":"NMIMS University","correspondingAuthor":false,"prefix":"","firstName":"Shreya","middleName":"","lastName":"Jain","suffix":""},{"id":406905520,"identity":"1709e176-321c-4afd-8866-bdd0463fa3e4","order_by":2,"name":"Pankti Doshi","email":"","orcid":"","institution":"NMIMS University","correspondingAuthor":false,"prefix":"","firstName":"Pankti","middleName":"","lastName":"Doshi","suffix":""}],"badges":[],"createdAt":"2025-01-21 05:53:03","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5870405/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5870405/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":74918181,"identity":"de90b598-40cf-4af3-be10-a74fa58e741d","added_by":"auto","created_at":"2025-01-28 10:12:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1177759,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerFormat.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5870405/v1_covered_cff56f6a-007d-47d1-8dd4-9d4f17fcc4a5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Discerning Human and AI-Generated Content in Short- Form Text","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Generative Artificial Intelligence, LLM, ChatGPT, Scraping, Fake Reviews,","lastPublishedDoi":"10.21203/rs.3.rs-5870405/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5870405/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the exponential rise in AI-powered language models, distinguishing human-generated text from AI-generated content has become increasingly vital for combating misinformation and maintaining trust on online platforms. This study explores the unique challenge of identifying whether casual, short-form user reviews on e-commerce websites are authored by humans or generated by AI. A comprehensive dataset comprising over 60,000 genuine reviews and 17,645 AI-generated reviews, spanning various product categories, was created through web scraping and the use of advanced language models. Leveraging robust feature engineering, model development, and statistical analysis, this research demonstrates the potential to reliably classify human and AI-generated content in informal, short-form contexts.","manuscriptTitle":"Discerning Human and AI-Generated Content in Short- Form Text","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-28 10:04:37","doi":"10.21203/rs.3.rs-5870405/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2025-01-25T03:05:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-01-25T03:04:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2025-01-21T05:37:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"a87e8edc-b2b3-441d-b8e6-1a1f7295ecdf","owner":[],"postedDate":"January 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-01-28T10:04:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-28 10:04:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5870405","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5870405","identity":"rs-5870405","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.