TERN: Type-Aware Evidence Reasoning for Multimodal Fake News Detection

TERN: Type-Aware Evidence Reasoning for Multimodal Fake News 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 TERN: Type-Aware Evidence Reasoning for Multimodal Fake News Detection HongYu Jin, Mingshu Zhang, Yaxuan Wang, Yuechuan Zhang, Bin Wei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9206268/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 proliferation of multimodal fake news on social media poses a persistent threat to public opinion and information credibility. Existing multimodal detection methods typically adopt a unified fusion strategy for all samples and learn entangled representations where deceptive patterns and semantic content are mixed. As a result, they struggle to (i) account for heterogeneous deception mechanisms such as image tampering and text--image mismatch, and (ii) perform hierarchical reasoning over multiple sources of evidence. To address these limitations, we propose TERN, a type-aware evidence reasoning network for multimodal fake news detection. TERN is built upon three key components. First, a type discovery module leverages contrastive learning and prototype-based clustering in the image feature space to automatically uncover latent deception types without manual annotations. Second, a type--semantic disentanglement module explicitly separates type-discriminative information from content semantics, mitigating spurious correlations between topics and veracity. Third, a type-guided hierarchical evidence fusion module generates textual, visual authenticity, and cross-modal consistency evidence, and adaptively integrates them via type-conditioned attention. Experiments on four public benchmarks---MR2-Chinese, MR2-English, Weibo, and PHEME---demonstrate that TERN outperforms strong multimodal baselines. On average, TERN achieves 93.21% accuracy and 91.09% F1-score, with clear gains in Matthews correlation coefficient, indicating more balanced decisions under class imbalance. Fake news detection multimodal learning type-aware fusion evidence reasoning representation disentanglement social media analytics 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-9206268","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":617548463,"identity":"8a9e68ad-02d2-4987-8ae0-d928d109249a","order_by":0,"name":"HongYu Jin","email":"","orcid":"","institution":"Chinese People's Armed Police Force Engineering University","correspondingAuthor":false,"prefix":"","firstName":"HongYu","middleName":"","lastName":"Jin","suffix":""},{"id":617548464,"identity":"0ad86582-dad5-4916-a006-73644fc9ae64","order_by":1,"name":"Mingshu Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYHACxgcJFTZybOztB4jWwmzw4UyaMR/PmQSitbBJzmw7nDhPwsGAOPXy044/kOZtO5zeJsGQwPCjYhthLYyzcwyMec6l57ZJNx5g7Dlzm7AWZukchmSeMuvcNpkDCcyMbURoYZNOf3CYh405nU0iwYA4LTzSCYaNM9qcE4jXIiGdY8wADGTDNmAgHyTKL/Kz05//AEalvHx7+8EHPyqI0IICDpCofhSMglEwCkYBLgAAnEQ6LeoyxpEAAAAASUVORK5CYII=","orcid":"","institution":"Chinese People's Armed Police Force Engineering University","correspondingAuthor":true,"prefix":"","firstName":"Mingshu","middleName":"","lastName":"Zhang","suffix":""},{"id":617548465,"identity":"391ab8ab-9e5b-4b54-bf29-24d21846775e","order_by":2,"name":"Yaxuan Wang","email":"","orcid":"","institution":"Chinese People's Armed Police Force Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Yaxuan","middleName":"","lastName":"Wang","suffix":""},{"id":617548466,"identity":"17f25450-c961-4618-a84a-aafc9d40aa9f","order_by":3,"name":"Yuechuan Zhang","email":"","orcid":"","institution":"Chinese People's Armed Police Force Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Yuechuan","middleName":"","lastName":"Zhang","suffix":""},{"id":617548467,"identity":"35951354-e50f-4877-9ff6-e5ea04e2cb6e","order_by":4,"name":"Bin Wei","email":"","orcid":"","institution":"Chinese People's Armed Police Force Engineering University","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Wei","suffix":""}],"badges":[],"createdAt":"2026-03-24 03:39:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9206268/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9206268/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108977833,"identity":"feb7731f-c0f4-4a00-8172-0593cfa0b505","added_by":"auto","created_at":"2026-05-11 11:33:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4755463,"visible":true,"origin":"","legend":"","description":"","filename":"TERN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9206268/v1_covered_bae393d8-bf1b-4f84-8553-1fbf7f376753.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TERN: Type-Aware Evidence Reasoning for Multimodal Fake News Detection","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":"Fake news detection, multimodal learning, type-aware fusion, evidence reasoning, representation disentanglement, social media analytics","lastPublishedDoi":"10.21203/rs.3.rs-9206268/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9206268/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The proliferation of multimodal fake news on social media poses a persistent threat to public opinion and information credibility. Existing multimodal detection methods typically adopt a unified fusion strategy for all samples and learn entangled representations where deceptive patterns and semantic content are mixed. As a result, they struggle to (i) account for heterogeneous deception mechanisms such as image tampering and text--image mismatch, and (ii) perform hierarchical reasoning over multiple sources of evidence. To address these limitations, we propose TERN, a type-aware evidence reasoning network for multimodal fake news detection. TERN is built upon three key components. First, a type discovery module leverages contrastive learning and prototype-based clustering in the image feature space to automatically uncover latent deception types without manual annotations. Second, a type--semantic disentanglement module explicitly separates type-discriminative information from content semantics, mitigating spurious correlations between topics and veracity. Third, a type-guided hierarchical evidence fusion module generates textual, visual authenticity, and cross-modal consistency evidence, and adaptively integrates them via type-conditioned attention. Experiments on four public benchmarks---MR2-Chinese, MR2-English, Weibo, and PHEME---demonstrate that TERN outperforms strong multimodal baselines. On average, TERN achieves 93.21\\% accuracy and 91.09\\% F1-score, with clear gains in Matthews correlation coefficient, indicating more balanced decisions under class imbalance.","manuscriptTitle":"TERN: Type-Aware Evidence Reasoning for Multimodal Fake News Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-07 22:32:28","doi":"10.21203/rs.3.rs-9206268/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":"2e3a27a0-1d0b-4b75-b05d-1909fa8be3b6","owner":[],"postedDate":"April 7th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-09T13:09:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-09T12:57:25+00:00","index":48,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T09:55:13+00:00","index":47,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T07:06:12+00:00","index":46,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T13:25:48+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-07 22:32:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9206268","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9206268","identity":"rs-9206268","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}