Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis

Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis | 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 Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis Oktay Karakus This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8871810/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Large-scale lyric corpora present unique challenges for data-driven analysis, including the absence of reliable annotations, multilingual content, and high levels of stylistic repetition. Most existing approaches rely on supervised classification, genre labels, or coarse document-level representations, limiting their ability to uncover latent semantic structure. We present a graph-based framework for unsupervised discovery and evaluation of semantic communities in K-pop lyrics using line-level semantic representations. By constructing a similarity graph over lyric texts and applying community detection, we uncover stable micro-theme communities without genre, artist, or language supervision. We further identify boundary-spanning songs via graph-theoretic bridge metrics and analyse their structural properties. Across multiple robustness settings, boundary-spanning lyrics exhibit higher lexical diversity and lower repetition compared to core community members, challenging the assumption that hook intensity or repetition drives cross-theme connectivity. Our framework is language-agnostic and applicable to unlabeled cultural text corpora. Lyric analysis Graph-based NLP Community detection Unsupervised learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 14 May, 2026 Reviews received at journal 02 May, 2026 Reviews received at journal 23 Apr, 2026 Reviewers agreed at journal 31 Mar, 2026 Reviewers agreed at journal 10 Mar, 2026 Reviewers invited by journal 09 Mar, 2026 Editor assigned by journal 17 Feb, 2026 Submission checks completed at journal 17 Feb, 2026 First submitted to journal 13 Feb, 2026 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-8871810","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":604750489,"identity":"ac48667c-c334-48ce-92aa-5e7c5b674139","order_by":0,"name":"Oktay Karakus","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIie2RsQrCMBBATwJ1Och6Qeg3BAKCn1OEuDgIgmNxqosfUMGPUARnpaBL1VU3u3TqoDgJDqY6SkNHhzy4HBfyuDsC4HD8IWSiMTYHLyuUPv/eb2ooYvxR1CfXU2T5CKGGIiaH7D6LQl/tk/xWDCRBM7kyTKuVFvaUWEaJaqdazebSKKglw3O14oMGkUWbYH0GxVC+QoA+MLxZFJ6zZxaFwSpuPoxiuvDCrrRIe2YwFiwI1VehsotlMBHnXic+JorS/rBR7uJRLrdzy/p00uwyHYU+n+xXULwkcd7NrsWuWvnFA+uvOBwOh6MOb4J3ShSQyH4yAAAAAElFTkSuQmCC","orcid":"","institution":"Cardiff University","correspondingAuthor":true,"prefix":"","firstName":"Oktay","middleName":"","lastName":"Karakus","suffix":""}],"badges":[],"createdAt":"2026-02-13 12:23:48","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8871810/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8871810/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104781291,"identity":"641b0a3e-eb58-4dab-8967-414a89ca2555","added_by":"auto","created_at":"2026-03-17 07:55:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":789319,"visible":true,"origin":"","legend":"","description":"","filename":"Kpop.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8871810/v1_covered_0a94bd1c-2294-4205-90d8-cc428d702d89.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"epj-data-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"epds","sideBox":"Learn more about [EPJ Data Science](https://epjdatascience.springeropen.com/)","snPcode":"13688","submissionUrl":"https://submission.springernature.com/new-submission/13688/3","title":"EPJ Data Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Lyric analysis, Graph-based NLP, Community detection, Unsupervised learning","lastPublishedDoi":"10.21203/rs.3.rs-8871810/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8871810/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large-scale lyric corpora present unique challenges for data-driven analysis, including the absence of reliable annotations, multilingual content, and high levels of stylistic repetition. Most existing approaches rely on supervised classification, genre labels, or coarse document-level representations, limiting their ability to uncover latent semantic structure. We present a graph-based framework for unsupervised discovery and evaluation of semantic communities in K-pop lyrics using line-level semantic representations. By constructing a similarity graph over lyric texts and applying community detection, we uncover stable micro-theme communities without genre, artist, or language supervision. We further identify boundary-spanning songs via graph-theoretic bridge metrics and analyse their structural properties. Across multiple robustness settings, boundary-spanning lyrics exhibit higher lexical diversity and lower repetition compared to core community members, challenging the assumption that hook intensity or repetition drives cross-theme connectivity. Our framework is language-agnostic and applicable to unlabeled cultural text corpora.","manuscriptTitle":"Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-13 07:28:41","doi":"10.21203/rs.3.rs-8871810/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-14T15:06:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T23:01:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-23T07:22:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1297326138064473418355118181868382217","date":"2026-03-31T16:49:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"340254807838362893416476229588060898075","date":"2026-03-10T13:15:26+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-10T00:44:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-17T08:05:35+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-17T08:05:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"EPJ Data Science","date":"2026-02-13T12:20:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"epj-data-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"epds","sideBox":"Learn more about [EPJ Data Science](https://epjdatascience.springeropen.com/)","snPcode":"13688","submissionUrl":"https://submission.springernature.com/new-submission/13688/3","title":"EPJ Data Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"811a40ad-abfb-46f0-b007-b1ef4e00c4e4","owner":[],"postedDate":"March 13th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-14T15:06:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T23:01:48+00:00","index":23,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-14T15:10:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-13 07:28:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8871810","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8871810","identity":"rs-8871810","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}