A Multi-Scale Adaptive Fusion Model for Multimodal Sarcasm Detection

A Multi-Scale Adaptive Fusion Model for Multimodal Sarcasm Detection | 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A Multi-Scale Adaptive Fusion Model for Multimodal Sarcasm Detection huixin wu, yang zang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6103602/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Sep, 2025 Read the published version in Discover Computing → Version 1 posted 13 You are reading this latest preprint version Abstract This paper proposes a Multi-Scale Adaptive Fusion Sarcasm Detection Model (MSAF-SDM) to address the challenges of information complexity and insufficient inter-modal collaboration in multimodal sarcasm detection. The model integrates multi-level features from text, audio, and video modalities, leveraging a dynamic attention mechanism and an adaptive weight allocation strategy to capture sarcasm-related cues across modalities. To enhance feature extraction capabilities, the text modality employs a dual multi-scale dilated window attention mechanism, the audio modality utilizes multi-scale temporal convolution, and the video modality incorporates multi-scale spatiotemporal convolution reinforced by auxiliary modal features. Experimental results demonstrate that MSAF-SDM achieves an accuracy of 89.04% and an F1-score of 87.68% on public datasets, significantly outperforming existing state-of-the-art models. Ablation studies further validate the effectiveness of the multimodal feature extraction and adaptive fusion mechanisms. This research provides a novel approach for tackling multimodal sarcasm detection tasks. Multimodal Sarcasm Detection Multi-Scale Feature Extraction Adaptive Fusion Mechanism Dilated Window Attention Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Sep, 2025 Read the published version in Discover Computing → Version 1 posted Editorial decision: Revision requested 19 May, 2025 Reviews received at journal 03 May, 2025 Reviewers agreed at journal 30 Apr, 2025 Reviewers agreed at journal 28 Apr, 2025 Reviews received at journal 21 Apr, 2025 Reviews received at journal 13 Apr, 2025 Reviewers agreed at journal 09 Apr, 2025 Reviewers agreed at journal 09 Apr, 2025 Reviewers invited by journal 31 Mar, 2025 Editor assigned by journal 27 Mar, 2025 Editor invited by journal 25 Mar, 2025 Submission checks completed at journal 25 Mar, 2025 First submitted to journal 25 Mar, 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-6103602","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":445064331,"identity":"02a218e1-c92a-41ae-9124-b209af3270e5","order_by":0,"name":"huixin wu","email":"","orcid":"","institution":"North China University of Water Resources and Electric Power","correspondingAuthor":false,"prefix":"","firstName":"huixin","middleName":"","lastName":"wu","suffix":""},{"id":445064332,"identity":"b7f5af20-9cd6-458d-99e0-db3d4337d8f0","order_by":1,"name":"yang zang","email":"data:image/png;base64,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","orcid":"","institution":"North China University of Water Resources and Electric Power","correspondingAuthor":true,"prefix":"","firstName":"yang","middleName":"","lastName":"zang","suffix":""}],"badges":[],"createdAt":"2025-02-25 09:23:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6103602/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6103602/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10791-025-09730-y","type":"published","date":"2025-09-25T15:57:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92430613,"identity":"0ee5c4b2-f23c-40ab-855e-996688cc7ae8","added_by":"auto","created_at":"2025-09-29 16:06:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1005597,"visible":true,"origin":"","legend":"","description":"","filename":"MSDF.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6103602/v1_covered_4a814361-6550-447a-a142-fc876b83f778.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multi-Scale Adaptive Fusion Model for Multimodal Sarcasm Detection","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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Multimodal Sarcasm Detection, Multi-Scale Feature Extraction, Adaptive Fusion Mechanism, Dilated Window Attention","lastPublishedDoi":"10.21203/rs.3.rs-6103602/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6103602/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper proposes a Multi-Scale Adaptive Fusion Sarcasm Detection Model (MSAF-SDM) to address the challenges of information complexity and insufficient inter-modal collaboration in multimodal sarcasm detection. The model integrates multi-level features from text, audio, and video modalities, leveraging a dynamic attention mechanism and an adaptive weight allocation strategy to capture sarcasm-related cues across modalities. To enhance feature extraction capabilities, the text modality employs a dual multi-scale dilated window attention mechanism, the audio modality utilizes multi-scale temporal convolution, and the video modality incorporates multi-scale spatiotemporal convolution reinforced by auxiliary modal features. Experimental results demonstrate that MSAF-SDM achieves an accuracy of 89.04% and an F1-score of 87.68% on public datasets, significantly outperforming existing state-of-the-art models. Ablation studies further validate the effectiveness of the multimodal feature extraction and adaptive fusion mechanisms. This research provides a novel approach for tackling multimodal sarcasm detection tasks.\u003c/p\u003e","manuscriptTitle":"A Multi-Scale Adaptive Fusion Model for Multimodal Sarcasm Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-21 08:28:21","doi":"10.21203/rs.3.rs-6103602/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-19T06:50:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-03T19:50:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"100638237745277473972399882478504916849","date":"2025-04-30T10:54:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"157136692393596482686457382894869194418","date":"2025-04-29T03:05:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-22T02:53:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-13T12:36:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"87043207136864451841781993183690578691","date":"2025-04-09T09:56:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319122245859717385755367087369750857639","date":"2025-04-09T08:00:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-31T07:13:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-27T10:32:03+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-03-25T10:18:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-25T08:39:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2025-03-25T08:38:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"065fd36c-8bc9-400c-b199-9d7566671cab","owner":[],"postedDate":"April 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-29T16:03:22+00:00","versionOfRecord":{"articleIdentity":"rs-6103602","link":"https://doi.org/10.1007/s10791-025-09730-y","journal":{"identity":"discover-computing","isVorOnly":false,"title":"Discover Computing"},"publishedOn":"2025-09-25 15:57:09","publishedOnDateReadable":"September 25th, 2025"},"versionCreatedAt":"2025-04-21 08:28:21","video":"","vorDoi":"10.1007/s10791-025-09730-y","vorDoiUrl":"https://doi.org/10.1007/s10791-025-09730-y","workflowStages":[]},"version":"v1","identity":"rs-6103602","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6103602","identity":"rs-6103602","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}