Aspect-level Multimodal Sentiment Analysis Model Based on Multi-scale Feature Extraction

Aspect-level Multimodal Sentiment Analysis Model Based on Multi-scale Feature Extraction | 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 Aspect-level Multimodal Sentiment Analysis Model Based on Multi-scale Feature Extraction Bocheng Miao, Changbo Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6622730/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract In existing multimodal sentiment analysis methods, only the last layer output of BERT is typically used for feature extraction, neglecting abundant information from intermediate layers. This paper proposes an Aspect-level Multimodal Sentiment Analysis Model with Multi-scale Feature Extraction (AMSAM-MFE). The model conducts sentiment analysis on both text and images. For text feature extraction, it incorporates a Multi-scale Layer module based on BERT and utilizes aspect terms to supervise text feature extraction, enhancing text processing performance. For image feature extraction, the model employs a pre-trained Resnest269 model with a specially designed Supervision Layer to improve effectiveness. For feature fusion, the Tensor Fusion Network method is adopted to achieve comprehensive interaction between visual and textual features. Experimental comparisons with other multimodal sentiment analysis models on Twitter2015 and Twitter2017 datasets demonstrate that the proposed multi-scale feature extraction model achieves improved accuracy and F1 scores in aspect-level multimodal sentiment analysis tasks, showing superior classification effectiveness compared to traditional multimodal sentiment analysis models. Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Aspect-level multimodal sentiment analysis multi-scale feature extraction aspect terms tensor fusion network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 26 Jun, 2025 Reviews received at journal 21 Jun, 2025 Reviews received at journal 15 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers invited by journal 04 Jun, 2025 Editor assigned by journal 28 May, 2025 Editor invited by journal 22 May, 2025 Submission checks completed at journal 21 May, 2025 First submitted to journal 08 May, 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-6622730","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":466218958,"identity":"0e8fa592-49a3-43b9-97e0-b5b6240e297f","order_by":0,"name":"Bocheng Miao","email":"","orcid":"","institution":"Beijing Institute of Graphic Communication","correspondingAuthor":false,"prefix":"","firstName":"Bocheng","middleName":"","lastName":"Miao","suffix":""},{"id":466218959,"identity":"ec62bf53-0a32-4f7a-b518-38470bc2508a","order_by":1,"name":"Changbo Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYHACNhCRwMDew3AAzD9AtBaeMyRrkciB8glpMbiR/OzBzx21efySbw8e/FLDIMd3I4HxcwEeLZIz0swNe88cL5acnZdwWOYYg7HkjQRm6Rl4tPBL5LBJ8LYdS9xwO8fgsGQDQ+KGGwlszDz4PALUIvkXpOXmGbCWeoJaQLZI87bVAA3nMTj4sYEhwYCQFsmeZ2bSsm0HiiV7gH5hOCZhOPPMw2ZpfFoMjic/k3zbVpfHz3728McfNTbyfMeTD37GpwUKDoNJoHskgBRjA2ENDAx1YJLxBzFqR8EoGAWjYMQBACHMT8O5mdj4AAAAAElFTkSuQmCC","orcid":"","institution":"Beijing Institute of Graphic Communication","correspondingAuthor":true,"prefix":"","firstName":"Changbo","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-05-08 17:23:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6622730/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6622730/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-16051-z","type":"published","date":"2025-08-27T15:57:55+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90345018,"identity":"b692f072-b401-4d30-b4eb-2ecff710ef60","added_by":"auto","created_at":"2025-09-01 16:09:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":504458,"visible":true,"origin":"","legend":"","description":"","filename":"AspectlevelMultimodalSentimentAnalysisModelBasedonMultiscaleFeatureExtraction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6622730/v1_covered_9ad340fb-cd22-4005-8f50-29bd9f2872ba.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Aspect-level Multimodal Sentiment Analysis Model Based on Multi-scale Feature Extraction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"Aspect-level multimodal sentiment analysis, multi-scale feature extraction, aspect terms, tensor fusion network","lastPublishedDoi":"10.21203/rs.3.rs-6622730/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6622730/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn existing multimodal sentiment analysis methods, only the last layer output of BERT is typically used for feature extraction, neglecting abundant information from intermediate layers. This paper proposes an Aspect-level Multimodal Sentiment Analysis Model with Multi-scale Feature Extraction (AMSAM-MFE). The model conducts sentiment analysis on both text and images. For text feature extraction, it incorporates a Multi-scale Layer module based on BERT and utilizes aspect terms to supervise text feature extraction, enhancing text processing performance. For image feature extraction, the model employs a pre-trained Resnest269 model with a specially designed Supervision Layer to improve effectiveness. For feature fusion, the Tensor Fusion Network method is adopted to achieve comprehensive interaction between visual and textual features. Experimental comparisons with other multimodal sentiment analysis models on Twitter2015 and Twitter2017 datasets demonstrate that the proposed multi-scale feature extraction model achieves improved accuracy and F1 scores in aspect-level multimodal sentiment analysis tasks, showing superior classification effectiveness compared to traditional multimodal sentiment analysis models.\u003c/p\u003e","manuscriptTitle":"Aspect-level Multimodal Sentiment Analysis Model Based on Multi-scale Feature Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-06 08:29:24","doi":"10.21203/rs.3.rs-6622730/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-26T14:12:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-21T04:10:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-15T13:19:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296481640101164924084065978406527828241","date":"2025-06-04T05:56:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"235338644548812777286984015258296324381","date":"2025-06-04T05:54:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-04T05:21:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-29T03:17:08+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-22T11:45:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-21T11:03:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-08T17:20:09+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":"9d35a2a3-c0b7-4281-b1be-6c9d1143b0b6","owner":[],"postedDate":"June 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":49494376,"name":"Physical sciences/Mathematics and computing"},{"id":49494377,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":49494378,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2025-09-01T16:05:26+00:00","versionOfRecord":{"articleIdentity":"rs-6622730","link":"https://doi.org/10.1038/s41598-025-16051-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-08-27 15:57:55","publishedOnDateReadable":"August 27th, 2025"},"versionCreatedAt":"2025-06-06 08:29:24","video":"","vorDoi":"10.1038/s41598-025-16051-z","vorDoiUrl":"https://doi.org/10.1038/s41598-025-16051-z","workflowStages":[]},"version":"v1","identity":"rs-6622730","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6622730","identity":"rs-6622730","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}