Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token

Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token | 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 Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token Xintong Wu, Peiting Tsai, Jing Yuan, Michael Yu, Greg Sun, Luyao Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9317342/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 Decentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate virtual asset transactions and governance. This study investigates the integration of Discord community sentiment with multi-modal financial data to enhance cryptocurrency price prediction within virtual world economies. We address: (1) identifying sentiment patterns within Decentraland's Discord community, and (2) evaluating the impact of multi-modal features on token return forecasting. Using a BERT-based large language model for sentiment analysis, we develop two LSTM architectures: a baseline incorporating historical prices and a multi-modal variant integrating sentiment scores, trading volume, and market capitalization. Results indicate predominantly neutral community sentiment with a positive skew. The multi-modal model significantly outperforms the price-only baseline in prediction accuracy. These findings demonstrate the predictive value of community-derived signals for virtual economy forecasting and establish a foundation for future research at the intersection of immersive virtual environments, natural language processing, and cryptocurrency market analysis. Large Language Models Sentiment Analysis Multi-Modal Learning Cryptocurrency Prediction Metaverse Blockchain Economics Full Text Additional Declarations The authors declare no competing interests. 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-9317342","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":617391234,"identity":"420dbef2-dfdd-440b-af40-baa236c43cca","order_by":0,"name":"Xintong Wu","email":"","orcid":"","institution":"University of Pennsylvania","correspondingAuthor":false,"prefix":"","firstName":"Xintong","middleName":"","lastName":"Wu","suffix":""},{"id":617391426,"identity":"9e0c5fbf-8ce1-4490-9d09-ed7e4da1690e","order_by":1,"name":"Peiting Tsai","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Peiting","middleName":"","lastName":"Tsai","suffix":""},{"id":617391427,"identity":"f9c0bda7-3bc3-494c-be0e-2f23a624752f","order_by":2,"name":"Jing Yuan","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Yuan","suffix":""},{"id":617391428,"identity":"03382715-f92e-4a7a-a2de-e507d89319e8","order_by":3,"name":"Michael Yu","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Yu","suffix":""},{"id":617391429,"identity":"facf7d7a-f36f-4cd7-9e6b-d1fa5d0d7854","order_by":4,"name":"Greg Sun","email":"","orcid":"","institution":"Microsoft","correspondingAuthor":false,"prefix":"","firstName":"Greg","middleName":"","lastName":"Sun","suffix":""},{"id":617391430,"identity":"98073b21-5c37-4da0-aa1c-33dc34437020","order_by":5,"name":"Luyao Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYBACPgbGxocfKpgZJEA8HmK0sDEwNxtLnCFNC3ubBG8bSVr4DzYbSM6zTpzZ3sD44G0bUbYcbHxQuC09cTbPAWbDuURpYWwE2rLtcOI8iQQ2aV6itDAzAv0yB6hF/gH7b+K0sIG0NBxOnC0B1E6cFh5GYCAfSzee2ZPYLDnnHBFa+PmPP3z4ocZadsbxwwc/vCkjQgsSYGwgTf0oGAWjYBSMAtwAAEoMMg1/KIrCAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-1183-2254","institution":"Duke Kunshan Univeristy","correspondingAuthor":true,"prefix":"","firstName":"Luyao","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-04-04 04:09:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9317342/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9317342/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106404244,"identity":"f051cf43-5e13-4ec4-b391-68613d044c25","added_by":"auto","created_at":"2026-04-08 09:15:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1342243,"visible":true,"origin":"","legend":"","description":"","filename":"ICBC2026MANAToken.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9317342/v1_covered_70fe2427-c3b7-41ef-9074-da3a93c6c7ec.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLeveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"f5260ff1-ce06-46d7-be00-5cab8ffb0742","identifier":"10.13039/501100001809","name":"National Natural Science Foundation of China","awardNumber":"12201266","order_by":0}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Large Language Models, Sentiment Analysis, Multi-Modal Learning, Cryptocurrency Prediction, Metaverse, Blockchain Economics ","lastPublishedDoi":"10.21203/rs.3.rs-9317342/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9317342/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDecentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate virtual asset transactions and governance. This study investigates the integration of Discord community sentiment with multi-modal financial data to enhance cryptocurrency price prediction within virtual world economies. We address: (1) identifying sentiment patterns within Decentraland's Discord community, and (2) evaluating the impact of multi-modal features on token return forecasting. Using a BERT-based large language model for sentiment analysis, we develop two LSTM architectures: a baseline incorporating historical prices and a multi-modal variant integrating sentiment scores, trading volume, and market capitalization. Results indicate predominantly neutral community sentiment with a positive skew. The multi-modal model significantly outperforms the price-only baseline in prediction accuracy. These findings demonstrate the predictive value of community-derived signals for virtual economy forecasting and establish a foundation for future research at the intersection of immersive virtual environments, natural language processing, and cryptocurrency market analysis.\u003c/p\u003e","manuscriptTitle":"Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-07 19:13:39","doi":"10.21203/rs.3.rs-9317342/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":"fefdd320-f915-40f0-95e3-0670bdd9102a","owner":[],"postedDate":"April 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-07T19:13:39+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-07 19:13:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9317342","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9317342","identity":"rs-9317342","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}