Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training

Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training | 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 Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training Liang Yang, Qi Yang, Jingjie Zeng, Tao Peng, Zhihao Yang, Hongfei Lin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4129332/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 The task of dialogue sentiment analysis aims to identify the sentiment polarity of utterances in the context of a dialogue. Pre-trained models often struggle to capture the logical structure of a dialogue, making this task challenging. To address this issue, we propose a dialogue sentiment analysis framework that leverages pre-training on dialogue structure. Our proposed framework includes three sub-tasks for pre-training: utterance order sorting, sentence backbone regularization, and sentiment shift detection. These tasks are designed to improve the model's ability to mine dialogue logical relationships and sentiment interactions. By focusing on learning the logical structure of dialogues and the perception of sentiment interactions, our framework is able to improve the performance of pre-trained models on recognizing the sentiment polarity of dialogues. This is demonstrated by the convincing results obtained on the public MEISD dataset. Dialogue Structure Sentiment Analysis Pre-training Model 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-4129332","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":283572326,"identity":"d421efa1-e7e4-4da4-beb5-7981f65abd34","order_by":0,"name":"Liang Yang","email":"","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Liang","middleName":"","lastName":"Yang","suffix":""},{"id":283572327,"identity":"aab9eeba-5c1a-4e11-b57b-6e7b620c3a6e","order_by":1,"name":"Qi Yang","email":"","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Yang","suffix":""},{"id":283572328,"identity":"62fe5d77-6639-471e-8d2f-36b7f0aad2ff","order_by":2,"name":"Jingjie Zeng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIie3PMQrCMBSA4VcCugS6xskrPBcRFC/iEhB0MSAI0kEkIugVHESvoItzS6CjXRUdBMGpg6OjaQY7mTo65B9Cm+bjNQAu1x/myRCAD1sAhEigQ7OJBURpgj1NPE0QWCHRR7MzyujfCJkl0fOGScdfapKimkJ5fmAwudp+jDCOF7FSnvTWqBjQeMwgfljvYojUhNCMsEGdmStaprw4HsX2Q6ppISnpKaHY5VNoIak3OHbFXpNojf3KgvZGDR5/J7VVdD+/grbYJCq6pUHT98tqf3pObCTMX8xjKVv4VwBQ9aXlq8vlcrmy3h1aVQPht5ozAAAAAElFTkSuQmCC","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Jingjie","middleName":"","lastName":"Zeng","suffix":""},{"id":283572329,"identity":"92880239-2cfe-40b8-8a02-7d7b07b58b8c","order_by":3,"name":"Tao Peng","email":"","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Peng","suffix":""},{"id":283572330,"identity":"297098e1-3eb8-4a51-8cf4-9a91515746b2","order_by":4,"name":"Zhihao Yang","email":"","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhihao","middleName":"","lastName":"Yang","suffix":""},{"id":283572331,"identity":"98417c1b-a128-432d-9e17-d071b7a70e06","order_by":5,"name":"Hongfei Lin","email":"","orcid":"","institution":"Dalian University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hongfei","middleName":"","lastName":"Lin","suffix":""}],"badges":[],"createdAt":"2024-03-19 10:07:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4129332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4129332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55264083,"identity":"f3d41783-c6da-48b7-ac05-1c018bedceb4","added_by":"auto","created_at":"2024-04-25 01:35:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":395694,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4129332/v1_covered_63451c88-1349-484a-8ebf-822503073935.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training","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":"Dialogue Structure, Sentiment Analysis, Pre-training Model","lastPublishedDoi":"10.21203/rs.3.rs-4129332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4129332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe task of dialogue sentiment analysis aims to identify the sentiment polarity of utterances in the context of a dialogue. Pre-trained models often struggle to capture the logical structure of a dialogue, making this task challenging. To address this issue, we propose a dialogue sentiment analysis framework that leverages pre-training on dialogue structure. Our proposed framework includes three sub-tasks for pre-training: utterance order sorting, sentence backbone regularization, and sentiment shift detection. These tasks are designed to improve the model's ability to mine dialogue logical relationships and sentiment interactions. By focusing on learning the logical structure of dialogues and the perception of sentiment interactions, our framework is able to improve the performance of pre-trained models on recognizing the sentiment polarity of dialogues. This is demonstrated by the convincing results obtained on the public MEISD dataset.\u003c/p\u003e","manuscriptTitle":"Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-28 11:15:58","doi":"10.21203/rs.3.rs-4129332/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":"677cc27f-5258-49ac-8463-55bf3cab8c01","owner":[],"postedDate":"March 28th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-21T23:12:11+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-28 11:15:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4129332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4129332","identity":"rs-4129332","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}