A Multi-Modal Sarcasm Detection Model Based onCue Learning

A Multi-Modal Sarcasm Detection Model Based onCue Learning | 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 A Multi-Modal Sarcasm Detection Model Based onCue Learning Ming Lu, Zhiqiang Dong, Litian Zhang, Ziming Guo, Xiaoming Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4862512/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted 5 You are reading this latest preprint version Abstract The rapid proliferation of internet data, particularly through social media, has amplified the need for effective sentiment analysis, including the complex task of sarcasm detection. This paper presents a novel multi-modal sarcasm detection model leveraging cue learning techniques to address the challenges posed by data scarcity, especially in low-resource languages. The proposed model builds upon the CLIP architecture, integrating text and image modalities to co-learn sarcasm cues. The methodology encompasses discrete prompt generation, learnable continuous vectors, and multi-modal fusion to enhance detection accuracy. The multi-modal fusion process demonstrates a symmetric integration of text and image data, leading to improved performance. Experimental results on the Twitter Multi-modal Sarcasm Detection Dataset (MSD) demonstrate significant performance improvements over traditional models, highlighting the model's robustness and adaptability in small-sample scenarios. This research contributes a practical solution for nuanced sentiment analysis, paving the way for advanced applications in public opinion monitoring and AI-driven decision-making processes. Physical sciences/Engineering Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 25 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted Reviewers invited by journal 15 Sep, 2024 Editor assigned by journal 09 Sep, 2024 Editor invited by journal 20 Aug, 2024 Submission checks completed at journal 19 Aug, 2024 First submitted to journal 05 Aug, 2024 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-4862512","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":354303843,"identity":"8e551719-0a2b-4c23-8caa-d884b8def020","order_by":0,"name":"Ming Lu","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Ming","middleName":"","lastName":"Lu","suffix":""},{"id":354303845,"identity":"801d594b-c05f-4bd7-819f-56c256201e9b","order_by":1,"name":"Zhiqiang Dong","email":"","orcid":"","institution":"CSSC Systems Engineering Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Zhiqiang","middleName":"","lastName":"Dong","suffix":""},{"id":354303846,"identity":"637138a3-c62c-4958-a79e-73edf9d35c28","order_by":2,"name":"Litian Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIiWNgGAWjYBACPmYGhgNAOgGIGR9DBQ3wamFjZoZrYTYmTgsDM5gGaWGTJk4LO//BAz931OXxz26/Vl3YZifPwN68TYKh5g5ehx3sPcNWLHHnTNntmW3Jhg08x8okGI49w+8X3jaexIYbOWm3eduYGRskcswkGBsO47flb5tE4nyglmLetnr7Bvk3hLUc5m0zSNxwI/0YM2/b4cQGCR6CWgwOy7YlJG68kcMsPePc8eQ2nrRii4RjuLXw8x98/PFtW13ivBvpDz8XlFXb9rMf3njjQw1uLUiABxIdbCAigRgNDAzsD4hTNwpGwSgYBSMOAADq91BKE9hTIwAAAABJRU5ErkJggg==","orcid":"","institution":"Beihang University","correspondingAuthor":true,"prefix":"","firstName":"Litian","middleName":"","lastName":"Zhang","suffix":""},{"id":354303848,"identity":"8cc7ab70-712a-4c5d-897a-3e89b772838e","order_by":3,"name":"Ziming Guo","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Ziming","middleName":"","lastName":"Guo","suffix":""},{"id":354303849,"identity":"0f69de30-d73d-4173-9eb8-0cd05b6ed914","order_by":4,"name":"Xiaoming Zhang","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-08-05 13:57:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4862512/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4862512/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-94266-w","type":"published","date":"2025-03-25T15:57:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":79605102,"identity":"e512e6f7-93c8-438a-af3a-eac9d5e800a7","added_by":"auto","created_at":"2025-03-31 16:10:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":405672,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4862512/v1_covered_fb8d1730-13c0-4397-8c31-e250650d09dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Multi-Modal Sarcasm Detection Model Based onCue Learning","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4862512/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4862512/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid proliferation of internet data, particularly through social media, has amplified the need for effective sentiment analysis, including the complex task of sarcasm detection. This paper presents a novel multi-modal sarcasm detection model leveraging cue learning techniques to address the challenges posed by data scarcity, especially in low-resource languages. The proposed model builds upon the CLIP architecture, integrating text and image modalities to co-learn sarcasm cues. The methodology encompasses discrete prompt generation, learnable continuous vectors, and multi-modal fusion to enhance detection accuracy. The multi-modal fusion process demonstrates a symmetric integration of text and image data, leading to improved performance. Experimental results on the Twitter Multi-modal Sarcasm Detection Dataset (MSD) demonstrate significant performance improvements over traditional models, highlighting the model's robustness and adaptability in small-sample scenarios. This research contributes a practical solution for nuanced sentiment analysis, paving the way for advanced applications in public opinion monitoring and AI-driven decision-making processes.","manuscriptTitle":"A Multi-Modal Sarcasm Detection Model Based onCue Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-16 07:19:46","doi":"10.21203/rs.3.rs-4862512/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2024-09-15T15:33:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-09T12:59:22+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-08-21T02:09:11+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-19T04:22:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-08-05T13:56:16+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":"2cd9e417-78a1-4242-b9b8-d7aa89f95932","owner":[],"postedDate":"September 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":37652512,"name":"Physical sciences/Engineering"},{"id":37652513,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-03-31T16:06:07+00:00","versionOfRecord":{"articleIdentity":"rs-4862512","link":"https://doi.org/10.1038/s41598-025-94266-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-03-25 15:57:50","publishedOnDateReadable":"March 25th, 2025"},"versionCreatedAt":"2024-09-16 07:19:46","video":"","vorDoi":"10.1038/s41598-025-94266-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-94266-w","workflowStages":[]},"version":"v1","identity":"rs-4862512","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4862512","identity":"rs-4862512","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}