{"id":"https://openalex.org/W4412394817","doi":"https://doi.org/10.1145/3726302.3730309","title":"WebClasSeg-25: A Dual-Classified Webpage Segmentation Dataset - Integrating Functional and Maturity-Based Analysis","display_name":"WebClasSeg-25: A Dual-Classified Webpage Segmentation Dataset - Integrating Functional and Maturity-Based Analysis","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412394817","doi":"https://doi.org/10.1145/3726302.3730309"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730309","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110321332","display_name":"Jonathan Gerber","orcid":null},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jonathan Gerber","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0003-6751-7944","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"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/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jasmin Saxer","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-1263-5757","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118976524","display_name":"Kimia Rabishokr","orcid":null},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Kimia Rabishokr","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0006-6594-002X","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"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/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bruno Kreiner","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0009-0007-5948-8345","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"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/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Weiler","raw_affiliation_strings":["Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8385-2537","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Zurich University of Applied Sciences, Winterthur, Switzerland","institution_ids":["https://openalex.org/I858936495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I858936495"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3792","last_page":"3801"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9955000281333923,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9725000262260437,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131987810134888},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.673934817314148},{"id":"https://openalex.org/keywords/maturity","display_name":"Maturity (psychological)","score":0.6576464176177979},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5971585512161255},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.47738116979599},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42967379093170166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4118238091468811},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38809746503829956},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2239723801612854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131987810134888},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.673934817314148},{"id":"https://openalex.org/C101433766","wikidata":"https://www.wikidata.org/wiki/Q3543263","display_name":"Maturity (psychological)","level":2,"score":0.6576464176177979},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5971585512161255},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.47738116979599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42967379093170166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4118238091468811},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38809746503829956},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2239723801612854},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcollection.zhaw.ch:11475/34669","is_oa":true,"landing_page_url":"https://hdl.handle.net/11475/34669","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"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730309","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730309","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730309","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2094164163","display_name":"Digital Transformation at the Local Tier of Government in Europe: Dynamics and Effects from a Cross-Countries and Over-Time Comparative Perspective (DIGILOG)","funder_award_id":"200839","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412394817.pdf","grobid_xml":"https://content.openalex.org/works/W4412394817.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2002238744","https://openalex.org/W2072240081","https://openalex.org/W2090193136","https://openalex.org/W2118860332","https://openalex.org/W2135769635","https://openalex.org/W2171149144","https://openalex.org/W2274492630","https://openalex.org/W2400661088","https://openalex.org/W2557898126","https://openalex.org/W2577359935","https://openalex.org/W2588006593","https://openalex.org/W2746892682","https://openalex.org/W2957505564","https://openalex.org/W2990138404","https://openalex.org/W3094448412","https://openalex.org/W3142760838","https://openalex.org/W3169038444","https://openalex.org/W4206845400","https://openalex.org/W4223909614","https://openalex.org/W4294740001","https://openalex.org/W4317659260","https://openalex.org/W4385298676","https://openalex.org/W4385879598","https://openalex.org/W4387850605","https://openalex.org/W4392964663","https://openalex.org/W4398176766","https://openalex.org/W4399715463","https://openalex.org/W4402377351","https://openalex.org/W4406077597"],"related_works":["https://openalex.org/W2791617766","https://openalex.org/W2010501276","https://openalex.org/W2055314256","https://openalex.org/W3122869223","https://openalex.org/W4388401032","https://openalex.org/W1989068941","https://openalex.org/W2364844596","https://openalex.org/W2916821761","https://openalex.org/W2387400882","https://openalex.org/W4366995163"],"abstract_inverted_index":{"Webpage":[0],"segmentation":[1,21,52],"is":[2,146],"a":[3,49,72,104,118,124],"crucial":[4],"task":[5],"in":[6,11,159,178],"web":[7,18,136,160],"analysis,":[8],"enabling":[9],"improvements":[10],"information":[12],"retrieval,":[13],"user":[14],"experience,":[15],"and":[16,28,40,62,88,111,141,162],"automated":[17],"understanding.However,":[19],"existing":[20],"datasets":[22],"often":[23],"lack":[24],"both":[25,60,114],"comprehensive":[26],"visual":[27,61,170],"textual":[29,63],"segmentation,":[30,171],"as":[31,33,83],"well":[32],"classification":[34,67,74,95,115],"systems":[35],"that":[36,54],"capture":[37],"the":[38,97,132,173],"functional":[39,80],"qualitative":[41],"aspects":[42],"of":[43,75,100,107,128,135,175],"webpages.In":[44],"this":[45],"paper,":[46],"we":[47,165],"introduce":[48],"novel":[50],"webpage":[51,101,129,151],"dataset":[53,145,177],"addresses":[55],"these":[56],"gaps":[57],"by":[58],"providing":[59],"segmentations,":[64],"alongside":[65],"two":[66],"frameworks.The":[68],"first":[69,167],"framework":[70],"defines":[71],"nominal":[73],"segments":[76],"based":[77],"on":[78,169],"their":[79,108],"roles,":[81],"such":[82],"main":[84],"content,":[85],"header,":[86],"footer,":[87],"navigation":[89],"bar.The":[90],"second":[91],"introduces":[92],"an":[93],"ordinal":[94],"assessing":[96],"digital":[98],"maturity":[99],"segments,":[102],"offering":[103],"structured":[105],"evaluation":[106],"design":[109,137],"evolution":[110,134],"complexity.By":[112],"integrating":[113],"schemes":[116],"into":[117],"single":[119],"dataset,":[120],"our":[121,144,176],"approach":[122],"enables":[123],"more":[125],"holistic":[126],"analysis":[127,161],"structures.Furthermore,":[130],"given":[131],"rapid":[133],"conventions,":[138],"content":[139],"structures,":[140],"technological":[142],"trends,":[143],"designed":[147],"to":[148],"reflect":[149],"contemporary":[150],"characteristics,":[152],"ensuring":[153],"its":[154],"relevance":[155],"for":[156],"modern":[157],"applications":[158],"machine":[163],"learning.Additionally,":[164],"provide":[166],"results":[168],"demonstrating":[172],"effectiveness":[174],"practical":[179],"applications.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
