A large-scale, granular topic classification system for scientific documents

A large-scale, granular topic classification system for scientific documents | 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 A large-scale, granular topic classification system for scientific documents Gard B. Jenset, Peter J. Bevan, Akarsh Jain This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6529718/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Knowledge Organisation Systems (KOSs) are crucial for search, retrieval, and analysis of the vast volumes of academic research, but KOSs are challenging to scale in a way that preserves granularity, breadth, and quality. Topics constructed with data-driven algorithms are a key type of KO in scientometrics, and developing high-quality systems for topic construction remains a cornerstone of scientometrics research. We present a topic construction and classification system that advances the state of the art in terms of breadth and granularity, consisting of over 29,000 topics organised into a four-level hierarchy, while achieving a high-quality as measured both quantitatively and via expert judgment. The paper makes three key contributions that address clear gaps in the current state of the art: first, documenting our approach to building a broad and granular topic solution; second, demonstrating that we can train a successful supervised classifier for a large number of topics to assign topics to new documents at scale; third, introducing a new evaluation measure, to measure topic coherence at scale. The paper exemplifies how citation clustering and Natural Language Processing (NLP) can be flexibly wielded together within scientometrics to advance the state of the art. Information Retrieval and Management Scientometrics Topic clustering Citation network Supervised classification Full Text Additional Declarations The authors declare potential competing interests as follows: All the authors were employed by Springer Nature while the work was carried out. Springer Nature is part-owned by the Holtzbrinck Group which also owns Digital Science, the provider of the Dimensions database used for the research. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-6529718","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":448780857,"identity":"69025e7d-04ee-474f-816f-b1ebf12a061d","order_by":0,"name":"Gard B. Jenset","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-7423-3112","institution":"Springer Nature","correspondingAuthor":true,"prefix":"","firstName":"Gard","middleName":"B.","lastName":"Jenset","suffix":""},{"id":448780858,"identity":"b452f33f-be58-4fcd-9c88-88d0413d2758","order_by":1,"name":"Peter J. Bevan","email":"","orcid":"","institution":"Springer Nature","correspondingAuthor":false,"prefix":"","firstName":"Peter","middleName":"J.","lastName":"Bevan","suffix":""},{"id":448780859,"identity":"48f955e9-e4ca-451f-af6f-da4e90f4c1b0","order_by":2,"name":"Akarsh Jain","email":"","orcid":"","institution":"Springer Nature","correspondingAuthor":false,"prefix":"","firstName":"Akarsh","middleName":"","lastName":"Jain","suffix":""}],"badges":[],"createdAt":"2025-04-25 14:13:10","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":true,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6529718/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-6529718/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105904662,"identity":"91aceca6-3205-4808-866b-4aa9582b8a0a","added_by":"auto","created_at":"2026-04-01 10:10:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":482161,"visible":true,"origin":"","legend":"","description":"","filename":"JensetetalCitationTopicsv022026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6529718/v2_covered_1e408687-8f46-424a-8cb0-dde46fcd3958.pdf"}],"financialInterests":"The authors declare potential competing interests as follows: All the authors were employed by Springer Nature while the work was carried out. Springer Nature is part-owned by the Holtzbrinck Group which also owns Digital Science, the provider of the Dimensions database used for the research.","formattedTitle":"A large-scale, granular topic classification system for scientific documents","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Springer Nature (United Kingdom)","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":"Scientometrics, Topic clustering, Citation network, Supervised classification","lastPublishedDoi":"10.21203/rs.3.rs-6529718/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6529718/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eKnowledge Organisation Systems (KOSs) are crucial for search, retrieval, and analysis of the vast volumes of academic research, but KOSs are challenging to scale in a way that preserves granularity, breadth, and quality. Topics constructed with data-driven algorithms are a key type of KO in scientometrics, and developing high-quality systems for topic construction remains a cornerstone of scientometrics research. We present a topic construction and classification system that advances the state of the art in terms of breadth and granularity, consisting of over 29,000 topics organised into a four-level hierarchy, while achieving a high-quality as measured both quantitatively and via expert judgment. The paper makes three key contributions that address clear gaps in the current state of the art: first, documenting our approach to building a broad and granular topic solution; second, demonstrating that we can train a successful supervised classifier for a large number of topics to assign topics to new documents at scale; third, introducing a new evaluation measure, to measure topic coherence at scale. The paper exemplifies how citation clustering and Natural Language Processing (NLP) can be flexibly wielded together within scientometrics to advance the state of the art.\u003c/p\u003e","manuscriptTitle":"A large-scale, granular topic classification system for scientific documents","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-03-31 18:14:27","doi":"10.21203/rs.3.rs-6529718/v2","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}},{"code":1,"date":"2025-04-28 03:06:53","doi":"10.21203/rs.3.rs-6529718/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":"c5d17a9b-4b74-477a-9d24-dae5ff09acc9","owner":[],"postedDate":"March 31st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47752489,"name":"Information Retrieval and Management"}],"tags":[],"updatedAt":"2025-04-28T03:06:53+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-31 18:14:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-6529718","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6529718","identity":"rs-6529718","version":["v2"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}