MindBugs: Self-Explanatory Disinformation Detection System with Human-in-the-loop

MindBugs: Self-Explanatory Disinformation Detection System with Human-in-the-loop | 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 MindBugs: Self-Explanatory Disinformation Detection System with Human-in-the-loop Ioana Cheres, Adrian Groza This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6981898/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract We introduce a self-explanatory, human-in-the-loop system for disinformation detection, that shifts the focus from binary classification to structured narrative understanding. Central to our approach is a hierarchical framework that organizes disinformation into interconnected narrative structures. This design not only enhances transparency, but also enables domain experts to intervene drastically in the classification process. We also present VER-1, a dataset of Eastern European disinformation and war propaganda, and evaluate our system on it alongside a COVID-19 corpus. The system performs best on VER-1, reflecting its focus on structured, campaign-driven disinformation rather than isolated falsehoods. The solution combines large language models with hierarchical clustering and textual entailment to construct and verify narrative structures. At each clustering step, the vector space is refined through synthetic data points, enabling semantically aligned texts to merge. This supports classification by narrative alignment and results in an interpretable, correctable, and expert-guided alternative to black-box models. Humanities/Complex networks Social science/Science, technology and society Scientific community and society/Developing world Scientific community and society/Scientific community/Culture Physical sciences/Mathematics and computing/Computer science Fake news detection Transparent AI Propaganda and disinformation detection Easter-Europe disinformation dataset Human-in-the-loop Explainable AI Narrative clustering Hierarchical classification Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Under Review 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-6981898","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":476989466,"identity":"11f63a16-c88a-4246-a82c-d8f4b4d21bca","order_by":0,"name":"Ioana Cheres","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYDACCQTJ+ABI8PCRooXZAKSFjUgtYMAGZhPUwj+7+diHD38s5ICMZ5Vfc+xk2BiYHz66gc+SO8eSZ85skzAGMsxuy25LBjqMzdg4B48WA4kcY2beBonEhhsJZrcltzEDtfCwSePXkv+Z+c8ficT5N9K/FUtuqydGSw4zM9DjiRtu5Jgxftx2mLAWiRtpxoy9QL8Y3sgplmbcdpyHjZmAX/hnJD9m+PGnTk7uRvrGjz+3Vdvzszc/fIxPCwpg5gGTxCoHAcYfpKgeBaNgFIyCEQMALPlCFMsqCYQAAAAASUVORK5CYII=","orcid":"","institution":"Technical University of Cluj-Napoca","correspondingAuthor":true,"prefix":"","firstName":"Ioana","middleName":"","lastName":"Cheres","suffix":""},{"id":476989467,"identity":"725b373e-d95e-4341-a822-8b89c97f828d","order_by":1,"name":"Adrian Groza","email":"","orcid":"","institution":"Technical University of Cluj-Napoca","correspondingAuthor":false,"prefix":"","firstName":"Adrian","middleName":"","lastName":"Groza","suffix":""}],"badges":[],"createdAt":"2025-06-26 09:36:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6981898/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6981898/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88866302,"identity":"857cf8d3-d837-4f1b-aed5-9dfa54cbd175","added_by":"auto","created_at":"2025-08-12 08:27:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":490492,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Finalfinalfinalarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6981898/v1_covered_e9d2d2fb-a26c-4d5c-92ac-489155db8f69.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"MindBugs: Self-Explanatory Disinformation Detection System with Human-in-the-loop","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Fake news detection, Transparent AI, Propaganda and disinformation detection, Easter-Europe disinformation dataset, Human-in-the-loop, Explainable AI, Narrative clustering, Hierarchical classification","lastPublishedDoi":"10.21203/rs.3.rs-6981898/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6981898/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We introduce a self-explanatory, human-in-the-loop system for disinformation detection, that shifts the focus from binary classification to structured narrative understanding. Central to our approach is a hierarchical framework that organizes disinformation into interconnected narrative structures. \r\nThis design not only enhances transparency, but also enables domain experts to intervene drastically in the classification process.\r\n\r\nWe also present VER-1, a dataset of Eastern European disinformation and war propaganda, and evaluate our system on it alongside a COVID-19 corpus. \r\nThe system performs best on VER-1, reflecting its focus on structured, campaign-driven disinformation rather than isolated falsehoods.\r\n\r\nThe solution combines large language models with hierarchical clustering and textual entailment to construct and verify narrative structures. At each clustering step, the vector space is refined through synthetic data points, enabling semantically aligned texts to merge. This supports classification by narrative alignment and results in an interpretable, correctable, and expert-guided alternative to black-box models.","manuscriptTitle":"MindBugs: Self-Explanatory Disinformation Detection System with Human-in-the-loop","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-12 08:19:26","doi":"10.21203/rs.3.rs-6981898/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-machine-intelligence","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natmachintell","sideBox":"Learn more about [Nature Machine Intelligence](http://www.nature.com/natmachintell/)","snPcode":"","submissionUrl":"","title":"Nature Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"710c5d91-75ef-4f21-bdea-b59dfade414f","owner":[],"postedDate":"August 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":50652343,"name":"Humanities/Complex networks"},{"id":50652344,"name":"Social science/Science, technology and society"},{"id":50652345,"name":"Scientific community and society/Developing world"},{"id":50652346,"name":"Scientific community and society/Scientific community/Culture"},{"id":50652347,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-09-19T16:00:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-12 08:19:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6981898","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6981898","identity":"rs-6981898","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}