{"id":"https://openalex.org/W2117209866","doi":"https://doi.org/10.1145/1062745.1062763","title":"The volume and evolution of web page templates","display_name":"The volume and evolution of web page templates","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2117209866","doi":"https://doi.org/10.1145/1062745.1062763","mag":"2117209866"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","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/A5053094139","display_name":"David Gibson","orcid":"https://orcid.org/0000-0002-7612-0530"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Gibson","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089487172","display_name":"Kunal Punera","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Punera","raw_affiliation_strings":["University of Texas at Austin, Austin, TX","Univ. of Texas at Austin, Austin TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. of Texas at Austin, Austin TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068021191","display_name":"Andrew Tomkins","orcid":"https://orcid.org/0000-0002-1611-9255"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Tomkins","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053094139"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":30.5298,"has_fulltext":false,"cited_by_count":169,"citation_normalized_percentile":{"value":0.99519922,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"830","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T13976","display_name":"Web visibility and informetrics","score":0.9887999892234802,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9350000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597768902778625},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.662016749382019},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.6309090256690979},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.6085100173950195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5961484909057617},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5667775869369507},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.5117099285125732},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4559091627597809},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.42273736000061035},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34456685185432434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597768902778625},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.662016749382019},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.6309090256690979},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.6085100173950195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5961484909057617},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5667775869369507},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.5117099285125732},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4559091627597809},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.42273736000061035},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34456685185432434},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1062745.1062763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.5192","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.5192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p830.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W180238871","https://openalex.org/W1647671624","https://openalex.org/W1989338554","https://openalex.org/W2040075907","https://openalex.org/W2124436456","https://openalex.org/W2146990843","https://openalex.org/W2152565070","https://openalex.org/W2156632103","https://openalex.org/W2157748587","https://openalex.org/W2167859982"],"related_works":["https://openalex.org/W4244466418","https://openalex.org/W2104062382","https://openalex.org/W2162878363","https://openalex.org/W2389021890","https://openalex.org/W3023343521","https://openalex.org/W2479325685","https://openalex.org/W3183791698","https://openalex.org/W2480873127","https://openalex.org/W3111710556","https://openalex.org/W4232302102"],"abstract_inverted_index":{"Web":[0],"pages":[1,16],"contain":[2],"a":[3,109,115],"combination":[4],"of":[5,32,40,68,84,95,111,117,129],"unique":[6],"content":[7,70,86,113],"and":[8,17,23,30,89,99,120,135,138],"template":[9,49,75,85],"material,":[10],"which":[11],"is":[12,74],"present":[13],"across":[14],"multiple":[15],"used":[18],"primarily":[19],"for":[20,48,132],"formatting,":[21],"navigation,":[22],"branding.":[24],"We":[25,124],"study":[26],"the":[27,36,69,72,78,82,90,126],"nature,":[28],"evolution,":[29],"prevalence":[31],"these":[33],"templates":[34,104],"on":[35,71],"web.":[37],"As":[38],"part":[39],"this":[41,130],"work,":[42],"we":[43],"develop":[44],"new":[45],"randomized":[46],"algorithms":[47],"extraction":[50],"that":[51,66],"perform":[52],"approximately":[53],"twenty":[54],"times":[55],"faster":[56],"than":[57],"existing":[58],"approaches":[59],"with":[60],"similar":[61],"quality.":[62],"Our":[63],"results":[64],"show":[65],"40--50%":[67],"web":[73],"content.":[76],"Over":[77],"last":[79],"eight":[80],"years,":[81],"fraction":[83,110],"has":[87],"doubled,":[88],"growth":[91,131],"shows":[92],"no":[93],"sign":[94],"abating.":[96],"Text,":[97],"links,":[98],"total":[100,112],"HTML":[101],"bytes":[102],"within":[103],"are":[105],"all":[106],"growing":[107],"as":[108],"at":[114],"rate":[116],"between":[118],"6":[119],"8%":[121],"per":[122],"year.":[123],"discuss":[125],"deleterious":[127],"implications":[128],"information":[133],"retrieval":[134],"ranking,":[136],"classification,":[137],"link":[139],"analysis.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
