Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM

Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM | 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 Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM Jianbo Zhao, Huailiang Liu, Yakai Wang, Weili Zhang, Xiaojin Zhang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3819255/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Mar, 2024 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract Danmakus are user-generated comments that overlay on videos, enabling real-time interactions between viewers and video content. The emotional orientation of danmakus can reflect the attitudes and opinions of viewers on video segments, which can help video platforms optimize video content recommendation and evaluate users’ abnormal emotion levels. Aiming at the problems of low transferability of traditional sentiment analysis methods in the danmaku domain, low accuracy of danmaku text segmentation, poor consistency of sentiment annotation, and insufficient semantic feature extraction, this paper proposes a video danmaku sentiment analysis method based on MIBE-RoBERTa-FF-BiLSTM. This paper constructs a "Bilibili Must-Watch List and Top Video Danmaku Sentiment Dataset” by ourselves, covering 10,000 positive and negative sentiment danmaku texts of 18 themes. A new word recognition algorithm based on mutual information (MI) and branch entropy (BE) is used to discover 2,610 irregular network popular new words from trigrams to heptagrams in the dataset, forming a domain lexicon. The Maslow’s hierarchy of needs theory is applied to guide the consistent sentiment annotation. The domain lexicon is integrated into the feature fusion layer of the RoBERTa-FF-BiLSTM model to fully learn the semantic features of word information, character information, and context information of danmaku texts and perform sentiment classification. Comparative experiments on the dataset show that the model proposed in this paper has the best comprehensive performance among the mainstream models for video danmaku text sentiment classification, with an F1 value of 94.06%, and its accuracy and robustness are also better than other models. The limitations of this paper are that the construction of the domain lexicon still requires manual participation and review, the semantic information of danmaku video content and the positive case preference are ignored. Biological sciences/Computational biology and bioinformatics/Computational neuroscience Biological sciences/Computational biology and bioinformatics/Data acquisition Biological sciences/Computational biology and bioinformatics/Data mining Biological sciences/Computational biology and bioinformatics/Data processing Biological sciences/Computational biology and bioinformatics/Machine learning Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology sentiment analysis new word discovery sentiment annotation feature fusion MIBE-RoBERTa-FF-BiLSTM Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 Mar, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 20 Feb, 2024 Reviews received at journal 11 Jan, 2024 Reviewers agreed at journal 11 Jan, 2024 Reviewers invited by journal 11 Jan, 2024 Editor assigned by journal 11 Jan, 2024 Editor invited by journal 30 Dec, 2023 Submission checks completed at journal 30 Dec, 2023 First submitted to journal 28 Dec, 2023 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-3819255","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":264700983,"identity":"370b7a86-bf7c-4459-9bba-eca8b21b6bb1","order_by":0,"name":"Jianbo Zhao","email":"data:image/png;base64,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","orcid":"","institution":"Xidian University","correspondingAuthor":true,"prefix":"","firstName":"Jianbo","middleName":"","lastName":"Zhao","suffix":""},{"id":264700984,"identity":"36fc8ebf-a0a3-46fa-b030-5ce788397c8f","order_by":1,"name":"Huailiang Liu","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Huailiang","middleName":"","lastName":"Liu","suffix":""},{"id":264700985,"identity":"13db54e0-2369-4e08-a362-da2212203b36","order_by":2,"name":"Yakai Wang","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Yakai","middleName":"","lastName":"Wang","suffix":""},{"id":264700986,"identity":"9eec6fc4-30aa-46b8-9a02-7d3b1e88ca0d","order_by":3,"name":"Weili Zhang","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Weili","middleName":"","lastName":"Zhang","suffix":""},{"id":264700987,"identity":"dafe7f67-fa8a-4e8f-aeae-5f09cc8b622d","order_by":4,"name":"Xiaojin Zhang","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Xiaojin","middleName":"","lastName":"Zhang","suffix":""},{"id":264700988,"identity":"1afe37ca-5779-4e37-98e3-9f204ea26596","order_by":5,"name":"Bowei Li","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Bowei","middleName":"","lastName":"Li","suffix":""},{"id":264700989,"identity":"28f42191-eb04-43eb-a329-43bdb9e20443","order_by":6,"name":"Tong Sun","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Sun","suffix":""},{"id":264700990,"identity":"be5e9f62-0d8c-45bf-89c6-d488e67b9686","order_by":7,"name":"Yanwei Qi","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Yanwei","middleName":"","lastName":"Qi","suffix":""},{"id":264700991,"identity":"8127bd1f-c850-4bce-b957-2db8f6a18536","order_by":8,"name":"Shanzhuang Zhang","email":"","orcid":"","institution":"Xidian University","correspondingAuthor":false,"prefix":"","firstName":"Shanzhuang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2023-12-29 03:14:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3819255/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3819255/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-56518-z","type":"published","date":"2024-03-09T15:01:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":52431895,"identity":"adcb5b1e-eadc-444f-a96e-cd366b13363d","added_by":"auto","created_at":"2024-03-11 15:09:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":834911,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3819255/v1_covered_25df5116-2db9-4dc5-b85f-a4ea0bbcbc80.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM","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":"sentiment analysis, new word discovery, sentiment annotation, feature fusion, MIBE-RoBERTa-FF-BiLSTM","lastPublishedDoi":"10.21203/rs.3.rs-3819255/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3819255/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDanmakus are user-generated comments that overlay on videos, enabling real-time interactions between viewers and video content. The emotional orientation of danmakus can reflect the attitudes and opinions of viewers on video segments, which can help video platforms optimize video content recommendation and evaluate users\u0026rsquo; abnormal emotion levels. Aiming at the problems of low transferability of traditional sentiment analysis methods in the danmaku domain, low accuracy of danmaku text segmentation, poor consistency of sentiment annotation, and insufficient semantic feature extraction, this paper proposes a video danmaku sentiment analysis method based on MIBE-RoBERTa-FF-BiLSTM. This paper constructs a \"Bilibili Must-Watch List and Top Video Danmaku Sentiment Dataset\u0026rdquo; by ourselves, covering 10,000 positive and negative sentiment danmaku texts of 18 themes. A new word recognition algorithm based on mutual information (MI) and branch entropy (BE) is used to discover 2,610 irregular network popular new words from trigrams to heptagrams in the dataset, forming a domain lexicon. The Maslow\u0026rsquo;s hierarchy of needs theory is applied to guide the consistent sentiment annotation. The domain lexicon is integrated into the feature fusion layer of the RoBERTa-FF-BiLSTM model to fully learn the semantic features of word information, character information, and context information of danmaku texts and perform sentiment classification. Comparative experiments on the dataset show that the model proposed in this paper has the best comprehensive performance among the mainstream models for video danmaku text sentiment classification, with an F1 value of 94.06%, and its accuracy and robustness are also better than other models. The limitations of this paper are that the construction of the domain lexicon still requires manual participation and review, the semantic information of danmaku video content and the positive case preference are ignored.\u003c/p\u003e","manuscriptTitle":"Sentiment Analysis of Video Danmakus Based on MIBE-RoBERTa-FF-BiLSTM","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-03 02:08:15","doi":"10.21203/rs.3.rs-3819255/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-02-20T06:25:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-12T03:25:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"4e808a5f-bc93-404f-856a-cc1bf4592a7b","date":"2024-01-12T02:47:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-12T01:31:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-12T01:28:01+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2023-12-30T07:20:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-12-30T07:14:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2023-12-29T03:08:15+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":"b5a4cfcc-f8f9-4072-aeea-ffab2eccf128","owner":[],"postedDate":"January 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":27889884,"name":"Biological sciences/Computational biology and bioinformatics/Computational neuroscience"},{"id":27889885,"name":"Biological sciences/Computational biology and bioinformatics/Data acquisition"},{"id":27889886,"name":"Biological sciences/Computational biology and bioinformatics/Data mining"},{"id":27889887,"name":"Biological sciences/Computational biology and bioinformatics/Data processing"},{"id":27889888,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":27889889,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":27889890,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2024-03-11T15:04:30+00:00","versionOfRecord":{"articleIdentity":"rs-3819255","link":"https://doi.org/10.1038/s41598-024-56518-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-03-09 15:01:18","publishedOnDateReadable":"March 9th, 2024"},"versionCreatedAt":"2024-01-03 02:08:15","video":"","vorDoi":"10.1038/s41598-024-56518-z","vorDoiUrl":"https://doi.org/10.1038/s41598-024-56518-z","workflowStages":[]},"version":"v1","identity":"rs-3819255","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3819255","identity":"rs-3819255","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}