Deep Learning Based Bi-Directional LSTM for Sentiment Analysis of Health App Reviews

Deep Learning Based Bi-Directional LSTM for Sentiment Analysis of Health App Reviews | 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 Deep Learning Based Bi-Directional LSTM for Sentiment Analysis of Health App Reviews Linda Varghese, Rajesh R Pai, Shavantrevva Bilakeri, Naganna Chetty This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8601406/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Health and wellness applications are used by many people to help with daily routines and long term habit formation. Users often share their experiences through app reviews, and these comments can be valuable for understanding what works well and where the design falls short. In this study, we examined these reviews using a deep learning approach built around a manually annotated set of 21,322 English entries. Before modelling, the text was cleaned, standardized, and balanced through random oversampling so that all sentiment categories were represented fairly. Deep learning models like CNN, RNN, LSTM, Bi- LSTM, and attention-based models were investigated in this study. A stacked Bi-LSTM with embedding dimensions, L2 regularized dropout found to be the best model attaining an accuracy of 93.55% with an F1- score of 94.00%. Earlier models relied on shallow or pre-trained embeddings whereas here the new model that has been proposed relies on data level balancing with specific targeted architectural refinements meant to improve upon health related generalization. This is realistically reflected by means of subtle sentiment expression capture to help in evaluation of health and wellness practical foundations. Health sciences/Health care Physical sciences/Mathematics and computing Sentiment Analysis Bi-LSTM CNN Deep Learning Models Attention App Reviews Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Mar, 2026 Reviews received at journal 01 Mar, 2026 Reviews received at journal 21 Feb, 2026 Reviews received at journal 20 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviewers agreed at journal 13 Feb, 2026 Reviewers agreed at journal 12 Feb, 2026 Reviewers invited by journal 11 Feb, 2026 Editor invited by journal 28 Jan, 2026 Editor assigned by journal 22 Jan, 2026 Submission checks completed at journal 22 Jan, 2026 First submitted to journal 14 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-8601406","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":591055616,"identity":"34f62e59-f004-4473-aab6-759116a19b3b","order_by":0,"name":"Linda Varghese","email":"","orcid":"","institution":"Manipal Academy of Higher Education","correspondingAuthor":false,"prefix":"","firstName":"Linda","middleName":"","lastName":"Varghese","suffix":""},{"id":591055617,"identity":"1b29f157-30dd-4f0a-8b1e-552a6d54d06c","order_by":1,"name":"Rajesh R Pai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYHCCBAbGBiDFzHwASEowMLADKR7itLAlQLQwE9bCANHCwGMA4RHSYt5+4OHDnzsY8vjbeb5u+LnDIo+/mYHxwds23FpkziQkG/OeYSiWOMy77WbvGQkgg4HZcC4eLRIMCWnSjG0MiQ1ALTd42ySADAY2aV58WvgfpP/8CdQy/zDPs5t/gVrmH2Zg/41Xi0RCGgNQQeKGwzxst0G2bADawoxfy4NkoDMkig0Ps5ndlgUzGJsl55zD57CcxI8/22zy5M4ffnbzbVtdntzx5oMf3pTh1gKMggSQzgQYNwEWTXgA+wGoSriWUTAKRsEoGAWoAAAfUVC7vLZG6QAAAABJRU5ErkJggg==","orcid":"","institution":"Manipal Academy of Higher Education","correspondingAuthor":true,"prefix":"","firstName":"Rajesh","middleName":"R","lastName":"Pai","suffix":""},{"id":591055618,"identity":"7688e430-0476-44d2-a26e-9c643ac6a17b","order_by":2,"name":"Shavantrevva Bilakeri","email":"","orcid":"","institution":"Manipal Academy of Higher Education","correspondingAuthor":false,"prefix":"","firstName":"Shavantrevva","middleName":"","lastName":"Bilakeri","suffix":""},{"id":591055620,"identity":"6d39984c-5775-4d02-a13b-21272f47a2eb","order_by":3,"name":"Naganna Chetty","email":"","orcid":"","institution":"Nitte University","correspondingAuthor":false,"prefix":"","firstName":"Naganna","middleName":"","lastName":"Chetty","suffix":""}],"badges":[],"createdAt":"2026-01-14 11:53:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8601406/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8601406/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102728425,"identity":"17ab0bfc-1962-4d59-918c-260caeb4292d","added_by":"auto","created_at":"2026-02-16 03:34:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":518875,"visible":true,"origin":"","legend":"","description":"","filename":"DeeplearningScientificreports21Jan2026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8601406/v1_covered_d14c6d72-61e4-432c-ac37-433206baa435.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Learning Based Bi-Directional LSTM for Sentiment Analysis of Health App Reviews","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":"Sentiment Analysis, Bi-LSTM, CNN, Deep Learning Models, Attention, App Reviews","lastPublishedDoi":"10.21203/rs.3.rs-8601406/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8601406/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Health and wellness applications are used by many people to help with daily routines and long term habit formation. Users often share their experiences through app reviews, and these comments can be valuable for understanding what works well and where the design falls short. In this study, we examined these reviews using a deep learning approach built around a manually annotated set of 21,322 English entries. Before modelling, the text was cleaned, standardized, and balanced through random oversampling so that all sentiment categories were represented fairly. Deep learning models like CNN, RNN, LSTM, Bi- LSTM, and attention-based models were investigated in this study. A stacked Bi-LSTM with embedding dimensions, L2 regularized dropout found to be the best model attaining an accuracy of 93.55% with an F1- score of 94.00%. Earlier models relied on shallow or pre-trained embeddings whereas here the new model that has been proposed relies on data level balancing with specific targeted architectural refinements meant to improve upon health related generalization. This is realistically reflected by means of subtle sentiment expression capture to help in evaluation of health and wellness practical foundations.","manuscriptTitle":"Deep Learning Based Bi-Directional LSTM for Sentiment Analysis of Health App Reviews","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-16 03:34:31","doi":"10.21203/rs.3.rs-8601406/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-17T19:38:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-01T16:23:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-21T16:11:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-21T03:45:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"339867613562084796153262262489666706007","date":"2026-02-13T17:05:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"249575161079397165956129671465639009955","date":"2026-02-13T13:13:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170093346952669226232602614212457307659","date":"2026-02-13T10:20:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"219713554539207661860791409608967422360","date":"2026-02-12T07:47:42+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-11T09:02:30+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-28T14:35:33+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-22T06:55:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-22T06:51:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-14T11:46:32+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":"dd6ac836-a5b3-46e8-b7c3-3fd73e6469bc","owner":[],"postedDate":"February 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62902546,"name":"Health sciences/Health care"},{"id":62902547,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-17T05:08:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-16 03:34:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8601406","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8601406","identity":"rs-8601406","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}