A Deep Learning Approach for Multilingual Sentiment Analysis

A Deep Learning Approach for Multilingual Sentiment Analysis | 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 A Deep Learning Approach for Multilingual Sentiment Analysis Bablu Pramanik, Santanu Modak, Chayan Paul This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7000230/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 Sentiment analysis is pivotal for extracting insights from user-generated content across multilingual digital platforms. While traditional methods perform well in monolingual settings, they often struggle with the complexities of linguistic diversity, including syntactic variations, data scarcity in low-resource languages, and cross-lingual domain shifts. This study addresses these challenges by proposing a hybrid deep learning framework that synergizes the strengths of transformer-based models, sequential learning, and graph-based reasoning for robust multilingual sentiment analysis. Leveraging the Amazon Multilingual Review Dataset—spanning English, German, French, Spanish, Japanese, and Chinese—it evaluates standalone models (mBERT, BiLSTM, GNN) and novel hybrid architectures (BERT-BiLSTM, GNN-BERT) enhanced with attention mechanisms. In experiments demonstrate that hybrid models consistently outperform standalone approaches, with GNN-BERT achieving a 93.4% F1-score by effectively integrating contextual embeddings, sequential dependencies, and relational structures. Key contributions include: ( 1 ) a scalable framework for language-agnostic sentiment classification, ( 2 ) rigorous per-language evaluation revealing performance disparities (e.g., 92.2% F1 for English vs. 84.5% for Arabic), and ( 3 ) solutions for low-resource language challenges through cross-lingual transfer. The study also highlights the role of attention mechanisms in improving interpretability by identifying sentiment-relevant tokens. These advancements bridge critical gaps in multilingual NLP, offering practical applications in e-commerce and social media analytics. For future work, it outlines directions including zero-shot transfer learning, handling code-switching, and integrating multimodal sentiment analysis to further broaden real-world applicability. Multilingual sentiment analysis hybrid deep learning transformer models cross-lingual transfer attention mechanisms 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-7000230","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":511380071,"identity":"d5af6eaf-32c5-48ea-8889-c5b080961ec2","order_by":0,"name":"Bablu Pramanik","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYBACAwYexgNgFnsDiGtBlBYGiBYeEGUgQYoWiQQwSViLOfvZA4d5GOzs+SWfX93wo0CCgb+9OwGvFsuevASgluTEmbNzym72AB0mcebsBvwOO5BjANRyIMHgdk7aDR6gFgOJXAJazr8Ba7G3v3km7eYforTcgNjCuEGC/dhtomyxnPEu4eAcg+TEGWdy2G7LGEjwEPSLOX/uwQdvKoAh1n782c03f2zk+Nt78WuBOg9E8EBIIpTDAfsDUlSPglEwCkbBCAIA7+1HMd5qjxAAAAAASUVORK5CYII=","orcid":"","institution":"Swami Vivekananda University","correspondingAuthor":true,"prefix":"","firstName":"Bablu","middleName":"","lastName":"Pramanik","suffix":""},{"id":511380072,"identity":"a29ed4c7-3d79-463a-b346-edec4a18fe51","order_by":1,"name":"Santanu Modak","email":"","orcid":"","institution":"Bengal College of Engineering and Technology","correspondingAuthor":false,"prefix":"","firstName":"Santanu","middleName":"","lastName":"Modak","suffix":""},{"id":511380074,"identity":"6406381c-f6db-4952-a468-8821fe92ab00","order_by":2,"name":"Chayan Paul","email":"","orcid":"","institution":"Swami Vivekananda University","correspondingAuthor":false,"prefix":"","firstName":"Chayan","middleName":"","lastName":"Paul","suffix":""}],"badges":[],"createdAt":"2025-06-29 02:08:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7000230/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7000230/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100360768,"identity":"32071c3f-0f87-46c5-a274-ae400cd01b8e","added_by":"auto","created_at":"2026-01-16 07:42:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":661843,"visible":true,"origin":"","legend":"","description":"","filename":"ADeepLearningApproachforMultilingualSentimentAnalysis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7000230/v1_covered_e29d6ca3-80ac-408f-907a-208c7a5375c1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Deep Learning Approach for Multilingual Sentiment Analysis","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":"Multilingual sentiment analysis, hybrid deep learning, transformer models, cross-lingual transfer, attention mechanisms","lastPublishedDoi":"10.21203/rs.3.rs-7000230/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7000230/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSentiment analysis is pivotal for extracting insights from user-generated content across multilingual digital platforms. While traditional methods perform well in monolingual settings, they often struggle with the complexities of linguistic diversity, including syntactic variations, data scarcity in low-resource languages, and cross-lingual domain shifts. This study addresses these challenges by proposing a hybrid deep learning framework that synergizes the strengths of transformer-based models, sequential learning, and graph-based reasoning for robust multilingual sentiment analysis. Leveraging the Amazon Multilingual Review Dataset\u0026mdash;spanning English, German, French, Spanish, Japanese, and Chinese\u0026mdash;it evaluates standalone models (mBERT, BiLSTM, GNN) and novel hybrid architectures (BERT-BiLSTM, GNN-BERT) enhanced with attention mechanisms. In experiments demonstrate that hybrid models consistently outperform standalone approaches, with GNN-BERT achieving a 93.4% F1-score by effectively integrating contextual embeddings, sequential dependencies, and relational structures. Key contributions include: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) a scalable framework for language-agnostic sentiment classification, (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) rigorous per-language evaluation revealing performance disparities (e.g., 92.2% F1 for English vs. 84.5% for Arabic), and (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) solutions for low-resource language challenges through cross-lingual transfer. The study also highlights the role of attention mechanisms in improving interpretability by identifying sentiment-relevant tokens. These advancements bridge critical gaps in multilingual NLP, offering practical applications in e-commerce and social media analytics. For future work, it outlines directions including zero-shot transfer learning, handling code-switching, and integrating multimodal sentiment analysis to further broaden real-world applicability.\u003c/p\u003e","manuscriptTitle":"A Deep Learning Approach for Multilingual Sentiment Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 06:31:05","doi":"10.21203/rs.3.rs-7000230/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":"daacc838-5cde-4050-9b5a-65089816db36","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-11T21:23:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-11 06:31:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7000230","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7000230","identity":"rs-7000230","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}