Dynamic Optimization of min-df in the GreedSum Algorithm for Enhanced Extractive Summarization

Dynamic Optimization of min-df in the GreedSum Algorithm for Enhanced Extractive Summarization | 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 Dynamic Optimization of min-df in the GreedSum Algorithm for Enhanced Extractive Summarization Shakarim Aubakirov, Iskander Akhmetov, Alexander Gelbukh, Rustam Mussabayev This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6224538/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 Jun, 2025 Read the published version in Artificial Intelligence Review → Version 1 posted 12 You are reading this latest preprint version Abstract This study introduces a dynamic optimization technique for the min-df (minimum document frequency) parameter in the GreedSum algorithm, aimed at improving extractive summarization. We applied geometric, percentile-based, and clustering-based methods on a dataset of 17,038 scientific articles from arXiv and PubMed.The results indicate a 2% improvement in ROUGE-1 F-measure compared to fixed min-df settings, achieving a peak F-measure of 45%. These findings demonstrate the potential of dynamic min-df tuning for better summa-rization, with future research directed at integrating deep learning models to further enhance accuracy and efficiency. Extractive Text Summarization GreedSum Dynamic Parameter Optimization TF-IDF Vectorization Natural Language Processing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 06 Jun, 2025 Read the published version in Artificial Intelligence Review → Version 1 posted Editorial decision: Revision requested 29 Mar, 2025 Reviews received at journal 25 Mar, 2025 Reviews received at journal 25 Mar, 2025 Reviews received at journal 22 Mar, 2025 Reviewers agreed at journal 22 Mar, 2025 Reviewers agreed at journal 17 Mar, 2025 Reviewers agreed at journal 17 Mar, 2025 Reviewers agreed at journal 17 Mar, 2025 Reviewers invited by journal 17 Mar, 2025 Editor assigned by journal 17 Mar, 2025 Submission checks completed at journal 14 Mar, 2025 First submitted to journal 14 Mar, 2025 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-6224538","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":430149539,"identity":"1fdc82de-9cc7-4647-8a9c-fd9949ded996","order_by":0,"name":"Shakarim Aubakirov","email":"","orcid":"","institution":"Kazakh-British Technical University","correspondingAuthor":false,"prefix":"","firstName":"Shakarim","middleName":"","lastName":"Aubakirov","suffix":""},{"id":430149540,"identity":"68ef89db-d066-4973-98bd-9ff34a014831","order_by":1,"name":"Iskander Akhmetov","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIie3PsQrCMBCA4ZODuCR2TSnUVxAyWnyWQqAuFSzu4mSXgmv7HIXMhQwuFR+ij9DFTaMdBJdkdMg/3XAf3AH4fH8YAUCcRtSfgbsSs0gkQupA4EuocCMLwEEUeXIMeD6K4qEhvHS2w4iQjcp4WO9aWacaIrASEJopzVf9rdXUkHh2spH5aMjTkH6YCFp+IeZryVTHV9cK5ZtExEaQHgRTMmzKsxB1tqVhZSHLsmwjpjZBgDhE+2Qd83tnMb+XU8u+z+fz+Vx6ATgRNIXr5b0dAAAAAElFTkSuQmCC","orcid":"","institution":"Kazakh-British Technical University","correspondingAuthor":true,"prefix":"","firstName":"Iskander","middleName":"","lastName":"Akhmetov","suffix":""},{"id":430149542,"identity":"77a5dca2-37e3-45ca-921b-bd10167029d7","order_by":2,"name":"Alexander Gelbukh","email":"","orcid":"","institution":"Instituto Politécnico Nacional (IPN)","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Gelbukh","suffix":""},{"id":430149544,"identity":"a1c8a04d-5900-4f2f-bbe2-b121b710ebe9","order_by":3,"name":"Rustam Mussabayev","email":"","orcid":"","institution":"Satbayev University","correspondingAuthor":false,"prefix":"","firstName":"Rustam","middleName":"","lastName":"Mussabayev","suffix":""}],"badges":[],"createdAt":"2025-03-14 08:23:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6224538/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6224538/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10462-025-11276-w","type":"published","date":"2025-06-06T15:57:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84243162,"identity":"c02a73ff-0f5f-42a3-95fb-93829788d84b","added_by":"auto","created_at":"2025-06-09 16:12:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1061926,"visible":true,"origin":"","legend":"","description":"","filename":"mindfpaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6224538/v1_covered_e749f153-f457-43a6-9c85-90b10169f7e5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dynamic Optimization of min-df in the GreedSum Algorithm for Enhanced Extractive Summarization","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Extractive Text Summarization, GreedSum Dynamic Parameter Optimization, TF-IDF Vectorization, Natural Language Processing","lastPublishedDoi":"10.21203/rs.3.rs-6224538/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6224538/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This study introduces a dynamic optimization technique for the min-df (minimum document frequency) parameter in the GreedSum algorithm, aimed at improving extractive summarization. We applied geometric, percentile-based, and clustering-based methods on a dataset of 17,038 scientific articles from arXiv and PubMed.The results indicate a 2% improvement in ROUGE-1 F-measure compared to fixed min-df settings, achieving a peak F-measure of 45%. These findings demonstrate the potential of dynamic min-df tuning for better summa-rization, with future research directed at integrating deep learning models to further enhance accuracy and efficiency.","manuscriptTitle":"Dynamic Optimization of min-df in the GreedSum Algorithm for Enhanced Extractive Summarization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-19 11:10:50","doi":"10.21203/rs.3.rs-6224538/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-29T07:28:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-25T23:53:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-25T14:48:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-23T01:40:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99326224472109705663746758605953017205","date":"2025-03-23T01:35:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1306856300304455791055689892304209395","date":"2025-03-17T22:14:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"198662387367641134481973183794588468241","date":"2025-03-17T13:00:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206920550557690192807107438789470758583","date":"2025-03-17T12:10:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-17T11:48:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-17T09:20:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-14T11:28:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Artificial Intelligence Review","date":"2025-03-14T08:18:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"artificial-intelligence-review","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aire","sideBox":"Learn more about [Artificial Intelligence Review](http://link.springer.com/journal/10462)","snPcode":"10462","submissionUrl":"https://submission.nature.com/new-submission/10462/3","title":"Artificial Intelligence Review","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"9244dd76-c773-42c0-8ac8-b634fb0b6f68","owner":[],"postedDate":"March 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-09T16:10:32+00:00","versionOfRecord":{"articleIdentity":"rs-6224538","link":"https://doi.org/10.1007/s10462-025-11276-w","journal":{"identity":"artificial-intelligence-review","isVorOnly":false,"title":"Artificial Intelligence Review"},"publishedOn":"2025-06-06 15:57:50","publishedOnDateReadable":"June 6th, 2025"},"versionCreatedAt":"2025-03-19 11:10:50","video":"","vorDoi":"10.1007/s10462-025-11276-w","vorDoiUrl":"https://doi.org/10.1007/s10462-025-11276-w","workflowStages":[]},"version":"v1","identity":"rs-6224538","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6224538","identity":"rs-6224538","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}