Comprehensive Smart Data Augmentation withMultiple Transformer Models for ImbalancedSentiment Classification

Comprehensive Smart Data Augmentation withMultiple Transformer Models for ImbalancedSentiment Classification | 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 Article Comprehensive Smart Data Augmentation withMultiple Transformer Models for ImbalancedSentiment Classification Prashant Upadhyaya, G. L. Saini, Ashish Dangi, Subodh Bansal, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8620573/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 17 You are reading this latest preprint version Abstract Class imbalance remains a persistent challenge in sentiment analysis, often causing models to favor majority classes whilefailing to capture minority opinions. This study investigates this issue using a real user feedback food-court review datasetand evaluates whether a diverse augmentation pipeline can mitigate its effects. The proposed approach integrates multipleaugmentation strategies to generate new, sentiment-consistent training instances instead of replicating existing samples.Incorporating these augmented examples into BERT-based classifiers resulted in notable gains: accuracy increased from81.70% to 90.64%, the weighted F1-score improved from 0.788 to 0.907, and major improvement in the negative recall,increasing from a baseline of 0.243 to 0.892. Highest relative gain in overall accuracy (12.64%), was reported for the ALBERTmodel i.e., improvement from 77.44% to 87.23%. The datasets were tested on other model and the consistent performancewas achieved for all other model using the smart augmentation approached, Thus, enabling the model to generalize moreeffectively and recognize positive, neutral, and negative sentiments with greater reliability. The findings demonstrate that amulti-strategy, context-aware augmentation process can substantially enhance transformer-based sentiment classificationunder imbalanced data conditions. These findings establish a critical efficiency-accuracy frontier for deploying deep learningmodels in real-world environments. Smart Augmentation is essential for maximizing the potential of transformer architectures insentiment analysis. It not only boosts the top-line accuracy for models like BERT by over 10% but also transforms the model’sreliability by nearly tripling its sensitivity to the negative class. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Feb, 2026 Reviews received at journal 19 Feb, 2026 Reviews received at journal 19 Feb, 2026 Reviews received at journal 17 Feb, 2026 Reviews received at journal 16 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviews received at journal 11 Feb, 2026 Reviewers agreed at journal 08 Feb, 2026 Reviewers agreed at journal 08 Feb, 2026 Reviewers agreed at journal 07 Feb, 2026 Reviewers agreed at journal 04 Feb, 2026 Reviewers agreed at journal 04 Feb, 2026 Reviewers invited by journal 03 Feb, 2026 Editor assigned by journal 03 Feb, 2026 Editor invited by journal 22 Jan, 2026 Submission checks completed at journal 22 Jan, 2026 First submitted to journal 22 Jan, 2026 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-8620573","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":585619878,"identity":"f84d204e-35c8-43b9-818a-97fd9d113d44","order_by":0,"name":"Prashant Upadhyaya","email":"","orcid":"","institution":"Chandigarh University","correspondingAuthor":false,"prefix":"","firstName":"Prashant","middleName":"","lastName":"Upadhyaya","suffix":""},{"id":585619885,"identity":"d27db68f-68cd-45c3-9ea4-9aef1e2392ea","order_by":1,"name":"G. L. Saini","email":"data:image/png;base64,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","orcid":"","institution":"Manipal University Jaipur","correspondingAuthor":true,"prefix":"","firstName":"G.","middleName":"L.","lastName":"Saini","suffix":""},{"id":585619886,"identity":"96914aba-8dd6-4637-8f55-fa77c8bbf26b","order_by":2,"name":"Ashish Dangi","email":"","orcid":"","institution":"Independent Researcher","correspondingAuthor":false,"prefix":"","firstName":"Ashish","middleName":"","lastName":"Dangi","suffix":""},{"id":585619887,"identity":"eca3b002-2dc0-41c5-8f36-2e7271f3567b","order_by":3,"name":"Subodh Bansal","email":"","orcid":"","institution":"Chandigarh University","correspondingAuthor":false,"prefix":"","firstName":"Subodh","middleName":"","lastName":"Bansal","suffix":""},{"id":585619889,"identity":"964339de-7b74-4bb3-97ae-e1f80ef5e7db","order_by":4,"name":"Anupam Vyas","email":"","orcid":"","institution":"Bundelkhand University","correspondingAuthor":false,"prefix":"","firstName":"Anupam","middleName":"","lastName":"Vyas","suffix":""}],"badges":[],"createdAt":"2026-01-16 15:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8620573/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8620573/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102028447,"identity":"22d740f6-a2b2-424e-b4c4-62213ad337e2","added_by":"auto","created_at":"2026-02-06 10:21:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3019431,"visible":true,"origin":"","legend":"","description":"","filename":"UpdatedComprehensiveSmartDataAugmentationScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8620573/v1_covered_13a6b113-ab02-4cd2-add1-625bf12ef0da.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comprehensive Smart Data Augmentation withMultiple Transformer Models for ImbalancedSentiment Classification","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8620573/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8620573/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Class imbalance remains a persistent challenge in sentiment analysis, often causing models to favor majority classes whilefailing to capture minority opinions. This study investigates this issue using a real user feedback food-court review datasetand evaluates whether a diverse augmentation pipeline can mitigate its effects. The proposed approach integrates multipleaugmentation strategies to generate new, sentiment-consistent training instances instead of replicating existing samples.Incorporating these augmented examples into BERT-based classifiers resulted in notable gains: accuracy increased from81.70% to 90.64%, the weighted F1-score improved from 0.788 to 0.907, and major improvement in the negative recall,increasing from a baseline of 0.243 to 0.892. Highest relative gain in overall accuracy (12.64%), was reported for the ALBERTmodel i.e., improvement from 77.44% to 87.23%. The datasets were tested on other model and the consistent performancewas achieved for all other model using the smart augmentation approached, Thus, enabling the model to generalize moreeffectively and recognize positive, neutral, and negative sentiments with greater reliability. The findings demonstrate that amulti-strategy, context-aware augmentation process can substantially enhance transformer-based sentiment classificationunder imbalanced data conditions. These findings establish a critical efficiency-accuracy frontier for deploying deep learningmodels in real-world environments. Smart Augmentation is essential for maximizing the potential of transformer architectures insentiment analysis. It not only boosts the top-line accuracy for models like BERT by over 10% but also transforms the model’sreliability by nearly tripling its sensitivity to the negative class.","manuscriptTitle":"Comprehensive Smart Data Augmentation withMultiple Transformer Models for ImbalancedSentiment Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-06 10:20:48","doi":"10.21203/rs.3.rs-8620573/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-20T17:13:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-20T03:30:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-19T10:04:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-17T14:16:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-16T06:38:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"263260157780402249414431162114949560634","date":"2026-02-13T07:36:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-11T08:20:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"212342745967426629910851560667837435381","date":"2026-02-09T04:23:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"328138694211685545504201924056896046647","date":"2026-02-08T15:41:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"6448693650653761412269243215973503103","date":"2026-02-07T16:10:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"193189846617232252158508756298927558824","date":"2026-02-04T10:32:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"112514937113280301618075813879609606694","date":"2026-02-04T07:31:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-03T15:18:31+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-03T14:07:28+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-22T17:43:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-22T05:46:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-22T05:45:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1d4d98e1-3e95-47a9-b882-569e13d91662","owner":[],"postedDate":"February 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62302331,"name":"Physical sciences/Engineering"},{"id":62302332,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-16T11:53:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-06 10:20:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8620573","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8620573","identity":"rs-8620573","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}