{"id":"https://openalex.org/W2037313016","doi":"https://doi.org/10.1145/2663792.2663803","title":"Clustering and Labeling a Web Scale Document Collection using Wikipedia clusters","display_name":"Clustering and Labeling a Web Scale Document Collection using Wikipedia clusters","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2037313016","doi":"https://doi.org/10.1145/2663792.2663803","mag":"2037313016"},"language":"en","primary_location":{"id":"doi:10.1145/2663792.2663803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2663792.2663803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Web-scale Knowledge Representation Retrieval &amp; Reasoning","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/A5015158048","display_name":"Richi Nayak","orcid":"https://orcid.org/0000-0002-9954-0159"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Richi Nayak","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044906461","display_name":"Rachel A. Mills","orcid":"https://orcid.org/0000-0002-9811-246X"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rachel Mills","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006899446","display_name":"Christopher De-Vries","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher De-Vries","raw_affiliation_strings":["chris.de.vries@celeraone.com, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"chris.de.vries@celeraone.com, Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045420626","display_name":"Shlomo Geva","orcid":"https://orcid.org/0000-0003-1340-2802"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shlomo Geva","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015158048"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":2.863,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9189449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9950000047683716,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9950000047683716,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9948999881744385,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8332325220108032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813869714736938},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7069034576416016},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6104271411895752},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4954026937484741},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4914737939834595},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45019155740737915},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36363518238067627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14537721872329712}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8332325220108032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813869714736938},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7069034576416016},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6104271411895752},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4954026937484741},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4914737939834595},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45019155740737915},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36363518238067627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14537721872329712},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2663792.2663803","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2663792.2663803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Web-scale Knowledge Representation Retrieval &amp; Reasoning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320972","display_name":"RMIT University","ror":"https://ror.org/04ttjf776"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W173263932","https://openalex.org/W188912188","https://openalex.org/W1531910981","https://openalex.org/W1577058187","https://openalex.org/W1685426458","https://openalex.org/W1966906268","https://openalex.org/W2016550647","https://openalex.org/W2036295879","https://openalex.org/W2065347041","https://openalex.org/W2150102617","https://openalex.org/W2963914943","https://openalex.org/W2979473749","https://openalex.org/W3101342260"],"related_works":["https://openalex.org/W1081706099","https://openalex.org/W2370730867","https://openalex.org/W2354431794","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"Clustering":[0],"is":[1,42,94,113],"an":[2],"important":[3],"technique":[4],"in":[5,16,103],"organising":[6],"and":[7,31,59,88,96,149],"categorising":[8],"web":[9,25,52,101,145],"scale":[10,134,146],"documents.":[11,82],"The":[12],"main":[13],"challenges":[14],"faced":[15],"clustering":[17,87,148,164],"the":[18,24,27,32,36,47,92,116,119,144,162],"billions":[19,56],"of":[20,35,57,63,79,98,100,126,159,193],"documents":[21,58,102],"available":[22],"on":[23,107,115,152],"are":[26,68,105],"processing":[28],"power":[29],"required":[30],"sheer":[33],"size":[34],"datasets":[37],"available.":[38],"More":[39],"importantly,":[40],"it":[41,130,139],"nigh":[43],"impossible":[44],"to":[45,74,108,142,173],"generate":[46],"labels":[48,80],"for":[49,81,161],"a":[50,60,75,86,123,132,157,175,191],"general":[51],"document":[53,66,147],"collection":[54],"containing":[55,166],"vast":[61],"taxonomy":[62],"topics.":[64],"However,":[65],"clusters":[67,180],"most":[69],"commonly":[70],"evaluated":[71,189],"by":[72],"comparison":[73],"ground":[76],"truth":[77],"set":[78,192],"This":[83,111],"paper":[84],"presents":[85],"labeling":[89,150],"solution":[90,112,165,176],"where":[91],"Wikipedia":[93,120,163],"clustered":[95],"hundreds":[97],"millions":[99],"ClueWeb12":[104],"mapped":[106],"those":[109],"clusters.":[110,169],"based":[114],"assumption":[117],"that":[118,129,138],"contains":[121],"such":[122,181],"wide":[124],"range":[125],"diverse":[127],"topics":[128],"represents":[131],"small":[133],"web.":[135],"We":[136],"found":[137],"was":[140],"possible":[141],"perform":[143],"process":[151],"one":[153],"desktop":[154],"computer":[155],"under":[156],"couple":[158],"days":[160],"about":[167],"1000":[168],"It":[170],"takes":[171],"longer":[172],"execute":[174],"with":[177],"finer":[178],"granularity":[179],"as":[182],"10,000":[183],"or":[184],"50,000.":[185],"These":[186],"results":[187],"were":[188],"using":[190],"external":[194],"data.":[195]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
