Benchmarking State of the Art Website Embedding Methods for Effective Processing and Analysis in the Public Sector

Benchmarking State of the Art Website Embedding Methods for Effective Processing and Analysis in the Public Sector | 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 Benchmarking State of the Art Website Embedding Methods for Effective Processing and Analysis in the Public Sector Jonathan Gerber, Jasmin Saxer, Bruno Kreiner, Andreas Weiler This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5664280/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Jun, 2025 Read the published version in Journal of Intelligent Information Systems → Version 1 posted 10 You are reading this latest preprint version Abstract The ability to understand and process websites is crucial across various domains. It lays the foundation for machine understanding of websites. Specifically, website embedding proves invaluable when monitoring local government websites within the context of digital transformation. In this paper, we present a comparison of different state-of-the-art website embedding methods and their capability of creating a reasonable website embedding for our specific task. The models consist of visual, mixed, and textual-based embedding methods. We compare the models with a baseline model which embeds the header section of a website. We measure the performance of the models using zero-shot and transfer learning. We evaluate the performance of the models on three different datasets. Additionally to the embedding scoring, we evaluate the classification performance on these datasets. From the zero-shot models Homepage2Vec with visual, a combination of visual and textual embedding, performs best in general over all datasets. When applying transfer learning, MarkupLM, a markup language-based model, outperforms the others in both cluster scoring as well as precision and F1-score in the classification task. However, time is an important factor when it comes to processing large data quantities. Thus, when additionally considering the time needed, our baseline model is a good alternative, being 1.88 times faster with a maximum decrease of 10 % in the F1-score. embedding evaluation website embedding website classification content monitoring cluster evaluation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 13 Jun, 2025 Read the published version in Journal of Intelligent Information Systems → Version 1 posted Editorial decision: Revision requested 02 Mar, 2025 Reviews received at journal 18 Feb, 2025 Reviews received at journal 10 Feb, 2025 Reviewers agreed at journal 12 Jan, 2025 Reviewers agreed at journal 09 Jan, 2025 Reviewers agreed at journal 08 Jan, 2025 Reviewers invited by journal 07 Jan, 2025 Editor assigned by journal 03 Jan, 2025 Submission checks completed at journal 03 Jan, 2025 First submitted to journal 17 Dec, 2024 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-5664280","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":397418600,"identity":"044968ed-15ce-4346-a817-267033de08f2","order_by":0,"name":"Jonathan Gerber","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYBACxgYYAQTMQCzHIAFmH8Cv5SCSFmOCWsAAWUtiAyEtzO29Bz9/3GGXx8C/+Njngop76fNnNz+TYKi5g9thPeeSJQ6eSS5mkHiWPHvGmeLcxjnHzCQYjj3DrWVGjoHEwTZmoHvOGDPztiXkNkskmN1gbDiMT4vxj4Nt9UAt5z8z8/5LSGeTSP9GSIsZ0JbDiQ38PczMvA0JCTwSOQRs6TljZnG27XhimwSbMfOMYwmGMyRyyn8kHMOtxbC9x/hGZVt1Yj//4cfMBTUJ8vIz0jcbfKjBo6UBymCTSEASTsBQiADycBb/ATzKRsEoGAWjYEQDAL8PWlwr5IiZAAAAAElFTkSuQmCC","orcid":"","institution":"Zurich University of Applied Science, ZHAW","correspondingAuthor":true,"prefix":"","firstName":"Jonathan","middleName":"","lastName":"Gerber","suffix":""},{"id":397418601,"identity":"ec51fd5c-e196-4d78-99e2-56ad5c98a898","order_by":1,"name":"Jasmin Saxer","email":"","orcid":"","institution":"Zurich University of Applied Science, ZHAW","correspondingAuthor":false,"prefix":"","firstName":"Jasmin","middleName":"","lastName":"Saxer","suffix":""},{"id":397418602,"identity":"47303f31-e1c4-4dda-b577-a8463ae64cfc","order_by":2,"name":"Bruno Kreiner","email":"","orcid":"","institution":"Zurich University of Applied Science, ZHAW","correspondingAuthor":false,"prefix":"","firstName":"Bruno","middleName":"","lastName":"Kreiner","suffix":""},{"id":397418603,"identity":"44a24d22-8031-4958-9041-2fd3e505ea26","order_by":3,"name":"Andreas Weiler","email":"","orcid":"","institution":"Zurich University of Applied Science, ZHAW","correspondingAuthor":false,"prefix":"","firstName":"Andreas","middleName":"","lastName":"Weiler","suffix":""}],"badges":[],"createdAt":"2024-12-17 19:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5664280/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5664280/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10844-025-00954-4","type":"published","date":"2025-06-13T15:57:47+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84727031,"identity":"592fd23e-ad8d-4981-b7cf-3552d1e08a7d","added_by":"auto","created_at":"2025-06-16 16:09:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":22178247,"visible":true,"origin":"","legend":"","description":"","filename":"JIISjournaledit3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5664280/v1_covered_5e79d899-dae8-48f6-b1d2-e5e32b3068d1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Benchmarking State of the Art Website Embedding Methods for Effective Processing and Analysis in the Public Sector","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":"journal-of-intelligent-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jiis","sideBox":"Learn more about [Journal of Intelligent Information Systems](http://link.springer.com/journal/10844)","snPcode":"10844","submissionUrl":"https://submission.nature.com/new-submission/10844/3","title":"Journal of Intelligent Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"embedding evaluation, website embedding, website classification, content monitoring, cluster evaluation","lastPublishedDoi":"10.21203/rs.3.rs-5664280/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5664280/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe ability to understand and process websites is crucial across various domains. It lays the foundation for machine understanding of websites. Specifically, website embedding proves invaluable when monitoring local government websites within the context of digital transformation. In this paper, we present a comparison of different state-of-the-art website embedding methods and their capability of creating a reasonable website embedding for our specific task. The models consist of visual, mixed, and textual-based embedding methods. We compare the models with a baseline model which embeds the header section of a website. We measure the performance of the models using zero-shot and transfer learning. We evaluate the performance of the models on three different datasets. Additionally to the embedding scoring, we evaluate the classification performance on these datasets. From the zero-shot models Homepage2Vec with visual, a combination of visual and textual embedding, performs best in general over all datasets. When applying transfer learning, MarkupLM, a markup language-based model, outperforms the others in both cluster scoring as well as precision and F1-score in the classification task. However, time is an important factor when it comes to processing large data quantities. Thus, when additionally considering the time needed, our baseline model is a good alternative, being 1.88 times faster with a maximum decrease of 10 % in the F1-score.\u003c/p\u003e","manuscriptTitle":"Benchmarking State of the Art Website Embedding Methods for Effective Processing and Analysis in the Public Sector","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-06 03:32:20","doi":"10.21203/rs.3.rs-5664280/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-02T17:13:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-18T11:36:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-10T16:55:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"74208888727521916950621698186560479820","date":"2025-01-13T03:07:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"85303843246805338405875551041046145352","date":"2025-01-09T12:20:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24337835407794898980382129346535185769","date":"2025-01-08T14:34:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-01-07T09:52:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-01-03T17:42:33+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-01-03T13:48:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Intelligent Information Systems","date":"2024-12-17T19:04:52+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-intelligent-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jiis","sideBox":"Learn more about [Journal of Intelligent Information Systems](http://link.springer.com/journal/10844)","snPcode":"10844","submissionUrl":"https://submission.nature.com/new-submission/10844/3","title":"Journal of Intelligent Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"05bac2da-64d3-43a1-ad74-bedf63936de5","owner":[],"postedDate":"January 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-16T16:06:23+00:00","versionOfRecord":{"articleIdentity":"rs-5664280","link":"https://doi.org/10.1007/s10844-025-00954-4","journal":{"identity":"journal-of-intelligent-information-systems","isVorOnly":false,"title":"Journal of Intelligent Information Systems"},"publishedOn":"2025-06-13 15:57:47","publishedOnDateReadable":"June 13th, 2025"},"versionCreatedAt":"2025-01-06 03:32:20","video":"","vorDoi":"10.1007/s10844-025-00954-4","vorDoiUrl":"https://doi.org/10.1007/s10844-025-00954-4","workflowStages":[]},"version":"v1","identity":"rs-5664280","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5664280","identity":"rs-5664280","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}