{"id":"https://openalex.org/W4411260892","doi":"https://doi.org/10.1007/s10844-025-00954-4","title":"Benchmarking state of the art website embedding methods for effective processing and analysis in the public sector","display_name":"Benchmarking state of the art website embedding methods for effective processing and analysis in the public sector","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411260892","doi":"https://doi.org/10.1007/s10844-025-00954-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/41710047"},"language":"en","primary_location":{"id":"doi:10.1007/s10844-025-00954-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-025-00954-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-025-00954-4.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10844-025-00954-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087346651","display_name":"Jonathan M. Gerber","orcid":"https://orcid.org/0000-0003-0524-8630"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jonathan Gerber","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland","institution_ids":["https://openalex.org/I200744771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099148559","display_name":"Jasmin Saxer","orcid":"https://orcid.org/0009-0000-1263-5757"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jasmin Saxer","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland","institution_ids":["https://openalex.org/I200744771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099148558","display_name":"Bruno Kreiner","orcid":"https://orcid.org/0009-0007-5948-8345"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bruno Kreiner","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland","institution_ids":["https://openalex.org/I200744771"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058264437","display_name":"Andreas Weiler","orcid":"https://orcid.org/0000-0002-8385-2537"},"institutions":[{"id":"https://openalex.org/I200744771","display_name":"ZHAW Zurich University of Applied Sciences","ror":null,"country_code":"CH","type":null,"lineage":["https://openalex.org/I200744771"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Weiler","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400 Zurich Switzerland","institution_ids":["https://openalex.org/I200744771"]},{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Science, ZHAW, Obere Kirchgasse 2, Winterthur, 8400, Zurich, Switzerland","institution_ids":["https://openalex.org/I200744771"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087346651"],"corresponding_institution_ids":["https://openalex.org/I200744771"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":9.6403,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97107345,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"64","issue":"1","first_page":"97","last_page":"120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10953","display_name":"E-Government and Public Services","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10953","display_name":"E-Government and Public Services","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10068","display_name":"Technology Adoption and User Behaviour","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.9443241357803345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8181860446929932},{"id":"https://openalex.org/keywords/public-sector","display_name":"Public sector","score":0.6454905271530151},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6031404733657837},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5201642513275146},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4741232693195343},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3576902151107788},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3278563618659973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24394291639328003},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.13700556755065918},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10784530639648438},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08857136964797974}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.9443241357803345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181860446929932},{"id":"https://openalex.org/C147859227","wikidata":"https://www.wikidata.org/wiki/Q294217","display_name":"Public sector","level":2,"score":0.6454905271530151},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6031404733657837},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5201642513275146},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4741232693195343},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3576902151107788},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3278563618659973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24394291639328003},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.13700556755065918},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10784530639648438},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08857136964797974},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10844-025-00954-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-025-00954-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-025-00954-4.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},{"id":"pmid:41710047","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41710047","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of intelligent information systems","raw_type":null},{"id":"pmh:oai:digitalcollection.zhaw.ch:11475/34670","is_oa":true,"landing_page_url":"https://hdl.handle.net/11475/34670","pdf_url":null,"source":{"id":"https://openalex.org/S4306401811","display_name":"Z\u00fcrcher Hochschule f\u00fcr Angewandte Wissenschaften digital collection (Zurich University of Applied Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200744771","host_organization_name":"ZHAW Zurich University of Applied Sciences","host_organization_lineage":["https://openalex.org/I200744771"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12909449","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12909449/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Intell Inf Syst","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10844-025-00954-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-025-00954-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10844-025-00954-4.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7166477347","display_name":null,"funder_award_id":"GR 200839GR 200839GR 200839GR 200839","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320337269","display_name":"Z\u00fcrcher Hochschule f\u00fcr Angewandte Wissenschaften","ror":"https://ror.org/05pmsvm27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411260892.pdf","grobid_xml":"https://content.openalex.org/works/W4411260892.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W1999376259","https://openalex.org/W2051224630","https://openalex.org/W2101241669","https://openalex.org/W2102766629","https://openalex.org/W2110319025","https://openalex.org/W2160196038","https://openalex.org/W2345381140","https://openalex.org/W2937423263","https://openalex.org/W2953490402","https://openalex.org/W2961671443","https://openalex.org/W2978399804","https://openalex.org/W2999962654","https://openalex.org/W3081176230","https://openalex.org/W3085706036","https://openalex.org/W3099461227","https://openalex.org/W3105625590","https://openalex.org/W3120844131","https://openalex.org/W3121976951","https://openalex.org/W3154224177","https://openalex.org/W3156333129","https://openalex.org/W3156636935","https://openalex.org/W3199545413","https://openalex.org/W3206324399","https://openalex.org/W4294740001","https://openalex.org/W4312862517","https://openalex.org/W4319006533","https://openalex.org/W4399715504","https://openalex.org/W4404968491","https://openalex.org/W6601700763","https://openalex.org/W6926018082"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"The":[0,63],"ability":[1],"to":[2,113,183],"understand":[3],"and":[4,50,69,98,136,168],"process":[5],"websites":[6,30],"is":[7,176,198],"crucial":[8],"across":[9],"various":[10],"domains.":[11],"It":[12],"lays":[13],"the":[14,32,75,83,91,94,103,106,114,119,126,158,171,192,214],"foundation":[15],"for":[16,59],"machine":[17],"understanding":[18],"of":[19,34,44,53,66,86,93,105,134,210],"websites.":[20],"Specifically,":[21],"website":[22,47,57],"embedding":[23,48,58,71,115],"proves":[24],"invaluable":[25],"when":[26,180,189],"monitoring":[27],"local":[28],"government":[29],"within":[31],"context":[33],"digital":[35],"transformation.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,117],"present":[41],"a":[42,55,78,87,132,153,199,207],"comparison":[43],"different":[45,110],"state-of-the-art":[46],"methods":[49],"their":[51],"capability":[52],"creating":[54],"reasonable":[56],"our":[60,195],"specific":[61],"task.":[62,173],"models":[64,76,95,107,128],"consist":[65],"visual,":[67,131],"mixed,":[68],"textual-based":[70],"methods.":[72],"We":[73,89,101],"compare":[74],"with":[77,130,206],"baseline":[79,196],"model":[80,197],"which":[81],"embeds":[82],"header":[84],"section":[85],"website.":[88],"measure":[90],"performance":[92,104,121],"using":[96],"zero-shot":[97,127],"transfer":[99,148],"learning.":[100],"evaluate":[102,118],"on":[108,122],"three":[109],"datasets.":[111,124,145],"Additionally":[112],"scoring,":[116],"classification":[120,172],"these":[123],"From":[125],"Homepage2Vec":[129],"combination":[133],"visual":[135],"textual":[137],"embedding,":[138],"performs":[139],"best":[140],"in":[141,160,170,213],"general":[142],"over":[143],"all":[144],"When":[146],"applying":[147],"learning,":[149],"TF-IDF":[150],"&":[151],"FNN,":[152],"text":[154],"based":[155],"model,":[156],"outperforms":[157],"others":[159],"both":[161],"cluster":[162],"scoring":[163],"as":[164,166],"well":[165],"precision":[167],"F1-score":[169],"However,":[174],"time":[175,193],"an":[177],"important":[178],"factor":[179],"it":[181],"comes":[182],"processing":[184],"large":[185],"data":[186],"quantities.":[187],"Thus,":[188],"additionally":[190],"considering":[191],"needed,":[194],"good":[200],"alternative,":[201],"being":[202],"1.88":[203],"times":[204],"faster":[205],"maximum":[208],"decrease":[209],"10":[211],"%":[212],"F1-score.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
