{"id":"https://openalex.org/W1989896487","doi":"https://doi.org/10.1145/2063576.2063636","title":"Legal document clustering with built-in topic segmentation","display_name":"Legal document clustering with built-in topic segmentation","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W1989896487","doi":"https://doi.org/10.1145/2063576.2063636","mag":"1989896487"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","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/A5089492071","display_name":"Qiang L\u00fc","orcid":"https://orcid.org/0000-0003-0554-7497"},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Lu","raw_affiliation_strings":["Thomson Reuters, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Reuters, Rochester, NY, USA","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025701458","display_name":"Jack G. Conrad","orcid":"https://orcid.org/0000-0001-9114-9385"},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack G. Conrad","raw_affiliation_strings":["Thomson Reuters, Saint Paul, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Reuters, Saint Paul, MN, USA","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011340349","display_name":"Khalid Al-Kofahi","orcid":null},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Al-Kofahi","raw_affiliation_strings":["Thomson Reuters, Saint Paul, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Reuters, Saint Paul, MN, USA","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026842467","display_name":"William Keenan","orcid":null},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Keenan","raw_affiliation_strings":["Thomson Reuters, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Reuters, Rochester, NY, USA","institution_ids":["https://openalex.org/I68384125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68384125"],"apc_list":null,"apc_paid":null,"fwci":3.0571,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.92498406,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9990000128746033,"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/T11719","display_name":"Data Quality and Management","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9909999966621399,"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":0.7872294783592224},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6976527571678162},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5643706917762756},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5226435661315918},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4934791326522827},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.46597692370414734},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45898115634918213},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.44357478618621826},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.44293084740638733},{"id":"https://openalex.org/keywords/legal-document","display_name":"Legal document","score":0.41466018557548523},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.41419243812561035},{"id":"https://openalex.org/keywords/legal-case","display_name":"Legal case","score":0.41133254766464233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38370153307914734},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3643779158592224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20645418763160706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872294783592224},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6976527571678162},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5643706917762756},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5226435661315918},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4934791326522827},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.46597692370414734},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45898115634918213},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44357478618621826},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.44293084740638733},{"id":"https://openalex.org/C2993995455","wikidata":"https://www.wikidata.org/wiki/Q3150005","display_name":"Legal document","level":2,"score":0.41466018557548523},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.41419243812561035},{"id":"https://openalex.org/C2778049185","wikidata":"https://www.wikidata.org/wiki/Q2334719","display_name":"Legal case","level":2,"score":0.41133254766464233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38370153307914734},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3643779158592224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20645418763160706},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063636","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1488461535","https://openalex.org/W1501500081","https://openalex.org/W1626945812","https://openalex.org/W1828401780","https://openalex.org/W1880262756","https://openalex.org/W1969351518","https://openalex.org/W1999236014","https://openalex.org/W2026450968","https://openalex.org/W2036216970","https://openalex.org/W2085904853","https://openalex.org/W2097739279","https://openalex.org/W2100958137","https://openalex.org/W2107743791","https://openalex.org/W2116929951","https://openalex.org/W2120804083","https://openalex.org/W2121602656","https://openalex.org/W2126399065","https://openalex.org/W2135266614","https://openalex.org/W2135909747","https://openalex.org/W2140920152","https://openalex.org/W2142522063","https://openalex.org/W2147152072","https://openalex.org/W2148818577","https://openalex.org/W2149041454","https://openalex.org/W2173213060","https://openalex.org/W2561675875","https://openalex.org/W2593713917","https://openalex.org/W3200920803","https://openalex.org/W4231510805","https://openalex.org/W4233135949","https://openalex.org/W4300874750","https://openalex.org/W6629169963","https://openalex.org/W6639619044","https://openalex.org/W6678457053"],"related_works":["https://openalex.org/W2972160875","https://openalex.org/W4385760465","https://openalex.org/W3217649904","https://openalex.org/W3128725805","https://openalex.org/W3187391786","https://openalex.org/W4309532058","https://openalex.org/W4387251649","https://openalex.org/W4385366071","https://openalex.org/W3184563164","https://openalex.org/W4308313401"],"abstract_inverted_index":{"Clustering":[0],"is":[1,109,233],"a":[2,62,81,112,127,136,168],"useful":[3],"tool":[4],"for":[5],"helping":[6],"users":[7],"navigate,":[8],"summarize,":[9],"and":[10,24,79,83,100,125,159,196,207],"organize":[11],"large":[12,183],"quantities":[13],"of":[14,30,44,49,57,64,87,122,130,185,209,225],"textual":[15],"documents":[16,69,94],"available":[17],"on":[18,95],"the":[19,38,55,58,96,106,117,175,205,210,223,226],"Internet,":[20,97],"in":[21,25,120],"news":[22],"sources,":[23],"digital":[26],"libraries.":[27],"A":[28],"variety":[29],"clustering":[31,140,170],"methods":[32],"have":[33,177,220],"also":[34],"been":[35,178],"applied":[36,179],"to":[37,181,203,235],"legal":[39,50,59,68,88,107,150,186,217],"domain,":[40],"with":[41,142,174],"various":[42],"degrees":[43],"success.":[45],"Some":[46],"unique":[47],"characteristics":[48],"content":[51],"as":[52,54,154],"well":[53],"nature":[56],"domain":[60,218,239],"present":[61],"number":[63],"challenges.":[65],"For":[66],"example,":[67],"are":[70,103],"often":[71],"multi-topical,":[72],"contain":[73],"carefully":[74],"crafted,":[75],"professional,":[76],"domain-specific":[77],"language,":[78],"possess":[80],"broad":[82],"unevenly":[84],"distributed":[85],"coverage":[86],"issues.":[89],"Moreover,":[90],"unlike":[91],"widely":[92],"accessible":[93],"where":[98],"search":[99],"categorization":[101],"services":[102],"generally":[104],"free,":[105],"profession":[108],"still":[110],"largely":[111],"fee-for-service":[113],"field":[114],"that":[115,222],"makes":[116],"quality":[118,224],"(e.g.,":[119],"terms":[121],"both":[123],"recall":[124],"precision)":[126],"key":[128],"differentiator":[129],"provided":[131],"services.":[132],"This":[133],"paper":[134],"introduces":[135],"classification-based":[137],"recursive":[138],"soft":[139],"algorithm":[141,147,176,232],"built-in":[143],"topic":[144],"segmentation.":[145],"The":[146],"leverages":[148],"existing":[149],"document":[151,157],"metadata":[152],"such":[153],"topical":[155],"classifications,":[156],"citations,":[158],"click":[160],"stream":[161],"data":[162],"from":[163],"user":[164],"behavior":[165],"databases,":[166],"into":[167],"comprehensive":[169],"framework.":[171],"Techniques":[172],"associated":[173],"successfully":[180],"very":[182],"databases":[184],"documents,":[187],"which":[188],"include":[189],"judicial":[190],"opinions,":[191],"statutes,":[192],"regulations,":[193],"administrative":[194],"materials":[195],"analytical":[197],"documents.":[198],"Extensive":[199],"evaluations":[200,214],"were":[201],"conducted":[202,215],"determine":[204],"efficiency":[206],"effectiveness":[208],"proposed":[211],"algorithm.":[212],"Subsequent":[213],"by":[216,238],"experts":[219],"demonstrated":[221],"resulting":[227],"clusters":[228],"based":[229],"upon":[230],"this":[231],"similar":[234],"those":[236],"created":[237],"experts.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}