Towards understanding news plagiarism: theoretical and experimental analysis

Towards understanding news plagiarism: theoretical and experimental 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 Towards understanding news plagiarism: theoretical and experimental analysis Ruxandra Marinescu-Ghemeci, Adrian Miclăuș, Ionuț Murarețu, Alexandru Popa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7069020/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Dec, 2025 Read the published version in World Wide Web → Version 1 posted 4 You are reading this latest preprint version Abstract In this paper we aim to improve the understanding of the news manipulation using a mathematical formalism. First, we develop a software that has the ability to crawl various news domains, to collect the news and to carry out similarity search between the collected news. Then, we create a mathematical model that uses temporal graphs based on the collected data. We also designed a random data generator for the above-mentioned model which we validate using four statistical tests: Kolmogorov-Smirnov test, Fisher's Exact test, Mann-Whitney U test and permutation test. We ran each of the 4 statistical tests on 100 randomly generated data counting how many times p-value is less than 0.05 or greater. On average, on at least 75% of instances we obtained a p-value greater or equal than 0.05. Then, our main result of the paper is that we formulate several combinatorial optimization problems and explain their relation to news plagiarism. We theoretically analyze each of these problems and prove NP-hardness and hardness-of approximation results. These results show that, unless P=NP, polynomial time exact algorithms for these problems do not exist. Finally, given the NP-hardness results, we formulate our problems as integer programs and use the state of the art solver, Gurobi, to solve them both on collected data and random generated data. Using multiple tests, we observe that a bugdet of around 40-60% of the total cost achieves an influence of at least 75% of the maximum value. News propagation Temporal Graphs NP-hard problems Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Dec, 2025 Read the published version in World Wide Web → Version 1 posted Editorial decision: Revision requested 04 Aug, 2025 Editor assigned by journal 10 Jul, 2025 Submission checks completed at journal 10 Jul, 2025 First submitted to journal 07 Jul, 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-7069020","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":495537872,"identity":"1662c02c-8017-4a0a-960a-cca05c27689f","order_by":0,"name":"Ruxandra Marinescu-Ghemeci","email":"","orcid":"","institution":"University of Bucharest","correspondingAuthor":false,"prefix":"","firstName":"Ruxandra","middleName":"","lastName":"Marinescu-Ghemeci","suffix":""},{"id":495537873,"identity":"554dd37a-6280-4266-9c9a-f406c65b94ed","order_by":1,"name":"Adrian Miclăuș","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYFCCBIYDIIqNgbkBSEnIgTgHHhCnhRGkxcIYrCWBgBYoAGupSGxAEcQC+NtzHx74uYMhmo/9YONnnj8S6fPDDj8E2mInp9uAXYvEmecGB3vPMOS28SQ2S/O2SeRuvJ1mANSSbGx2AIc1N9IYDvC2AbVIMDZI8zYAtcxOAGk5kLgNhxZ5oJaDfyFamn+DHGY4O/0DXi0GQC2Hoba0SfOwSSTIS+fgt8XwzDOGw7JALwD90mY5t03CcIN0TsGBBAPcfpE7nsb88W2bTe789sOHb7z5UycvPzt984cPFXZyOL0PARJITgWrNMCrHA3IN5CiehSMglEwCkYCAACmLWGhgiCvMQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Bucharest","correspondingAuthor":true,"prefix":"","firstName":"Adrian","middleName":"","lastName":"Miclăuș","suffix":""},{"id":495537874,"identity":"80341ad2-fbb4-44fd-a6a1-b0de0f4a5759","order_by":2,"name":"Ionuț Murarețu","email":"","orcid":"","institution":"University of Craiova","correspondingAuthor":false,"prefix":"","firstName":"Ionuț","middleName":"","lastName":"Murarețu","suffix":""},{"id":495537875,"identity":"db4a37f9-dddb-4293-a6d5-d3020b463a32","order_by":3,"name":"Alexandru Popa","email":"","orcid":"","institution":"University of Bucharest","correspondingAuthor":false,"prefix":"","firstName":"Alexandru","middleName":"","lastName":"Popa","suffix":""}],"badges":[],"createdAt":"2025-07-07 23:08:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7069020/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7069020/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11280-025-01387-3","type":"published","date":"2025-12-02T15:58:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97723953,"identity":"a7dddc26-a6ac-4138-98e2-9e518b2dd045","added_by":"auto","created_at":"2025-12-08 16:10:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":891086,"visible":true,"origin":"","legend":"","description":"","filename":"Towardsunderstandingnewsplagiarismrevised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7069020/v1_covered_1ea51945-2b9e-4746-974a-cc859447483a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards understanding news plagiarism: theoretical and experimental analysis","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":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"News propagation, Temporal Graphs, NP-hard problems","lastPublishedDoi":"10.21203/rs.3.rs-7069020/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7069020/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In this paper we aim to improve the understanding of the news manipulation using a mathematical formalism. First, we develop a software that has the ability to crawl various news domains, to collect the news and to carry out similarity search between the collected news. Then, we create a mathematical model that uses temporal graphs based on the collected data. \nWe also designed a random data generator for the above-mentioned model which we validate using four statistical tests: Kolmogorov-Smirnov test, Fisher's Exact test, Mann-Whitney U test and permutation test. We ran each of the 4 statistical tests on 100 randomly generated data counting how many times p-value is less than 0.05 or greater. On average, on at least 75% of instances we obtained a p-value greater or equal than 0.05. \nThen, our main result of the paper is that we formulate several combinatorial optimization problems and explain their relation to news plagiarism. We theoretically analyze each of these problems and prove NP-hardness and hardness-of approximation results. These results show that, unless P=NP, polynomial time exact algorithms for these problems do not exist. \nFinally, given the NP-hardness results, we formulate our problems as integer programs and use the state of the art solver, Gurobi, to solve them both on collected data and random generated data. Using multiple tests, we observe that a bugdet of around 40-60% of the total cost achieves an influence of at least 75% of the maximum value.","manuscriptTitle":"Towards understanding news plagiarism: theoretical and experimental analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-13 09:36:30","doi":"10.21203/rs.3.rs-7069020/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-04T16:23:33+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-10T13:46:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-10T13:45:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Wide Web","date":"2025-07-07T22:54:14+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ef2886aa-c9fd-4be5-9529-7ee2541a9c4e","owner":[],"postedDate":"August 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T16:03:57+00:00","versionOfRecord":{"articleIdentity":"rs-7069020","link":"https://doi.org/10.1007/s11280-025-01387-3","journal":{"identity":"world-wide-web","isVorOnly":false,"title":"World Wide Web"},"publishedOn":"2025-12-02 15:58:18","publishedOnDateReadable":"December 2nd, 2025"},"versionCreatedAt":"2025-08-13 09:36:30","video":"","vorDoi":"10.1007/s11280-025-01387-3","vorDoiUrl":"https://doi.org/10.1007/s11280-025-01387-3","workflowStages":[]},"version":"v1","identity":"rs-7069020","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7069020","identity":"rs-7069020","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}