{"id":"https://openalex.org/W1984928860","doi":"https://doi.org/10.1145/2745555.2746649","title":"DOM block clustering for enhanced sampling and evaluation","display_name":"DOM block clustering for enhanced sampling and evaluation","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W1984928860","doi":"https://doi.org/10.1145/2745555.2746649","mag":"1984928860"},"language":"en","primary_location":{"id":"doi:10.1145/2745555.2746649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2745555.2746649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Web for All Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057651456","display_name":"Simon Harper","orcid":"https://orcid.org/0000-0001-9301-5049"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Simon Harper","raw_affiliation_strings":["University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014876402","display_name":"Anwar Ahmad Moon","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anwar Ahmad Moon","raw_affiliation_strings":["University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083965427","display_name":"Markel Vigo","orcid":"https://orcid.org/0000-0003-4768-7623"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Markel Vigo","raw_affiliation_strings":["University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062163634","display_name":"Giorgio Brajnik","orcid":"https://orcid.org/0000-0002-0634-7676"},"institutions":[{"id":"https://openalex.org/I129043915","display_name":"University of Udine","ror":"https://ror.org/05ht0mh31","country_code":"IT","type":"education","lineage":["https://openalex.org/I129043915"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Brajnik","raw_affiliation_strings":["University of Udine, Italy","(University of Udine, Italy)"],"affiliations":[{"raw_affiliation_string":"University of Udine, Italy","institution_ids":["https://openalex.org/I129043915"]},{"raw_affiliation_string":"(University of Udine, Italy)","institution_ids":["https://openalex.org/I129043915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006201403","display_name":"Yeliz Ye\u015filada","orcid":"https://orcid.org/0000-0001-8501-0205"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Yeliz Yesilada","raw_affiliation_strings":["Middle East Technical University Northern Cyprus Campus, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University Northern Cyprus Campus, Turkey","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057651456"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":4.1376,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93084112,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12481","display_name":"Digital Accessibility for Disabilities","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"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/T12481","display_name":"Digital Accessibility for Disabilities","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783279418945312},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7651314735412598},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5194603800773621},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5151675939559937},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5001895427703857},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4993717670440674},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49770668148994446},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4918801784515381},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46593254804611206},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.462518572807312},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.458553284406662},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38709986209869385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34282827377319336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24044004082679749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19095036387443542},{"id":"https://openalex.org/keywords/web-design","display_name":"Web design","score":0.1583060920238495},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.10940146446228027},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09355303645133972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08865576982498169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783279418945312},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7651314735412598},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5194603800773621},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5151675939559937},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5001895427703857},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4993717670440674},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49770668148994446},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4918801784515381},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46593254804611206},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.462518572807312},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.458553284406662},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38709986209869385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34282827377319336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24044004082679749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19095036387443542},{"id":"https://openalex.org/C521306242","wikidata":"https://www.wikidata.org/wiki/Q190637","display_name":"Web design","level":3,"score":0.1583060920238495},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.10940146446228027},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09355303645133972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08865576982498169},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2745555.2746649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2745555.2746649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Web for All Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/f2d5a8d0-d9be-41cf-b977-bad214e1528c","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/f2d5a8d0-d9be-41cf-b977-bad214e1528c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Harper, S, Moon, A A, Vigo, M, Brajnik, G & Yesilada, Y 2015, DOM block clustering for enhanced sampling and evaluation. in Proceedings of the 12th Web for All Conference. https://doi.org/10.1145/2745555.2746649","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:air.uniud.it:11390/1179639","is_oa":false,"landing_page_url":"http://hdl.handle.net/11390/1179639","pdf_url":null,"source":{"id":"https://openalex.org/S4306401163","display_name":"Institutional Research Information System (University of Udine)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I129043915","host_organization_name":"University of Udine","host_organization_lineage":["https://openalex.org/I129043915"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1647641001","https://openalex.org/W1647671624","https://openalex.org/W1983416950","https://openalex.org/W2091482278","https://openalex.org/W2110907739","https://openalex.org/W2121353558","https://openalex.org/W2130807793","https://openalex.org/W2143845053","https://openalex.org/W2160933581","https://openalex.org/W2611200784"],"related_works":["https://openalex.org/W38260586","https://openalex.org/W4377003043","https://openalex.org/W1972854571","https://openalex.org/W2762277149","https://openalex.org/W3130985738","https://openalex.org/W3095158916","https://openalex.org/W52394763","https://openalex.org/W2051135816","https://openalex.org/W2592441986","https://openalex.org/W1963973829"],"abstract_inverted_index":{"Large":[0],"websites":[1,41],"are":[2,90,94,110],"difficult":[3],"to":[4,11,29,113,131,135,142,171],"evaluate":[5],"for":[6,120],"Web":[7,21],"Accessibility":[8],"compliance":[9],"due":[10],"the":[12,17,25,34,48,56,75,82,88,100,116,127,150],"shear":[13],"number":[14],"of":[15,19,47,87,103,107,185],"pages,":[16],"inaccuracy":[18],"current":[20],"evaluation":[22,57,76],"engines,":[23],"and":[24,85,147,176],"W3C":[26],"stated":[27],"need":[28,119,130],"include":[30],"human":[31],"evaluators":[32],"within":[33],"testing":[35],"regime.":[36],"This":[37,161],"makes":[38],"evaluating":[39,182],"large":[40,169],"all-but":[42],"technically":[43],"unfeasible.":[44],"Therefore,":[45],"sampling":[46],"pages":[49,108,151],"becomes":[50],"a":[51,104,121,144,172],"critical":[52],"first":[53],"step":[54],"in":[55,133,166],"process.":[58],"Current":[59],"methods":[60],"rely":[61],"on":[62,115,154],"drawing":[63],"random":[64],"samples,":[65,68],"best":[66],"guess":[67],"or":[69],"convenience":[70],"samples.":[71],"In":[72],"all":[73],"cases":[74],"results":[77],"cannot":[78],"be":[79,164,198],"trusted":[80],"because":[81],"underlying":[83],"structure":[84],"nature":[86],"site":[89],"not":[91],"known;":[92],"they":[93],"missing":[95],"'website":[96],"demographics'.":[97],"By":[98],"understanding":[99],"quantifiable":[101],"statistics":[102],"given":[105],"population":[106],"we":[109,118,129,193],"better":[111],"able":[112],"decide":[114],"coverage":[117,180],"full":[122],"review,":[123],"as":[124,126],"well":[125],"sample":[128],"draw":[132],"order":[134],"enact":[136],"an":[137,178],"evaluation.":[138],"Our":[139],"solution":[140],"is":[141],"crawl":[143],"website":[145],"comparing,":[146],"then":[148],"clustering,":[149],"discovered":[152],"based":[153],"Document":[155],"Object":[156],"Model":[157],"block":[158],"level":[159],"similarity.":[160],"technique":[162],"can":[163],"useful":[165],"reducing":[167],"very":[168],"sites":[170],"more":[173],"manageable":[174],"size,":[175],"allowing":[177],"80%":[179],"by":[181,188],"between":[183],"\u22480.1--4%":[184],"pages;":[186],"additionally,":[187],"refining":[189],"our":[190],"clustering":[191],"algorithm,":[192],"discuss":[194],"how":[195],"this":[196],"could":[197],"reduced":[199],"further.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}