Influence Prediction in Collaboration Networks: An Empirical Study on arXiv

Influence Prediction in Collaboration Networks: An Empirical Study on arXiv | 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 Influence Prediction in Collaboration Networks: An Empirical Study on arXiv Marina Lin, Laura P. Schaposnik, Raina Wu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7401473/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 This paper provides an empirical study of the Social Sphere Model for influence prediction, previously introduced by the authors, combining link prediction with top‑k centrality-based selection. We apply the model to the temporal arXiv General Relativity and Quantum Cosmology collaboration network, evaluating its performance under varying edge sampling rates and prediction horizons to reflect different levels of initial data completeness and network evolution. Accuracy is assessed using mean squared error in both link prediction and influence maximization tasks. The results show that the model effectively identifies latent influencers - nodes that are not initially central but later influential - and performs best with denser initial graphs. Among the similarity measures tested, the newly introduced RA-2 metric consistently yields the lowest prediction errors. These findings support the practical applicability of the model to predict real-world influence in evolving networks. link prediction centrality metrics vital nodes identification 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-7401473","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":512997604,"identity":"34af5d32-5783-4d04-ae48-7d0f8dff5065","order_by":0,"name":"Marina Lin","email":"","orcid":"","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Marina","middleName":"","lastName":"Lin","suffix":""},{"id":512997605,"identity":"0690a569-b080-43e0-924b-8a93796dc2b1","order_by":1,"name":"Laura P. Schaposnik","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYFACHjApx8AMothI0GJMupbEBgZitci3nz34uaCiLn3DceYHDB/KDhPWYnAmL1l6xpnDuRsOsxkwzjhHjBYJHgNp3rYDQC08DMy8bURokZ/BY/ybt60u3QCk5S8xWhhu8JgBbWFOAGthJEaLwZkcM2ugXwxnAv1ysOdcOhEOaz9jfBsYYvJ85w8/fPCjzJoIhwEBM4xxgDj1yFpGwSgYBaNgFGAFAHLqNa6nApzzAAAAAElFTkSuQmCC","orcid":"","institution":"University of Illinois at Chicago","correspondingAuthor":true,"prefix":"","firstName":"Laura","middleName":"P.","lastName":"Schaposnik","suffix":""},{"id":512997606,"identity":"631a1735-1947-48e7-bad3-00fb7d4de943","order_by":2,"name":"Raina Wu","email":"","orcid":"","institution":"Massachusetts Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Raina","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-08-18 16:09:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7401473/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7401473/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96918830,"identity":"5c6a0bfc-bbc9-48aa-b5a7-79e83ec4a066","added_by":"auto","created_at":"2025-11-27 14:12:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2169583,"visible":true,"origin":"","legend":"","description":"","filename":"InfluencePaper2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7401473/v1_covered_383386e1-67ff-4593-9bb8-4836b70dc10c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Influence Prediction in Collaboration Networks: An Empirical Study on arXiv","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":"link prediction, centrality metrics, vital nodes identification","lastPublishedDoi":"10.21203/rs.3.rs-7401473/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7401473/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper provides an empirical study of the Social Sphere Model for influence prediction, previously introduced by the authors, combining link prediction with top‑k centrality-based selection. We apply the model to the temporal arXiv General Relativity and Quantum Cosmology collaboration network, evaluating its performance under varying edge sampling rates and prediction horizons to reflect different levels of initial data completeness and network evolution. Accuracy is assessed using mean squared error in both link prediction and influence maximization tasks. The results show that the model effectively identifies latent influencers - nodes that are not initially central but later influential - and performs best with denser initial graphs. Among the similarity measures tested, the newly introduced RA-2 metric consistently yields the lowest prediction errors. These findings support the practical applicability of the model to predict real-world influence in evolving networks.","manuscriptTitle":"Influence Prediction in Collaboration Networks: An Empirical Study on arXiv","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 08:11:14","doi":"10.21203/rs.3.rs-7401473/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":"ff43009e-8816-4d34-9e7b-e216d54e779b","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-27T03:08:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-17 08:11:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7401473","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7401473","identity":"rs-7401473","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}