{"id":"https://openalex.org/W2155516811","doi":"https://doi.org/10.1145/1401890.1401952","title":"Mining multi-faceted overviews of arbitrary topics in a text collection","display_name":"Mining multi-faceted overviews of arbitrary topics in a text collection","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2155516811","doi":"https://doi.org/10.1145/1401890.1401952","mag":"2155516811"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5103583048","display_name":"Xu Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xu Ling","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048955398","display_name":"Qiaozhu Mei","orcid":"https://orcid.org/0000-0002-8640-1942"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaozhu Mei","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028518494","display_name":"ChengXiang Zhai","orcid":"https://orcid.org/0000-0002-6434-3702"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ChengXiang Zhai","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072847130","display_name":"Bruce R. Schatz","orcid":"https://orcid.org/0000-0001-5957-1711"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce Schatz","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103583048"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":8.7808,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9754228,"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":"497","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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":0.8513177633285522},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6534995436668396},{"id":"https://openalex.org/keywords/facet","display_name":"Facet (psychology)","score":0.6152786016464233},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6098037362098694},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5489481091499329},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4559384882450104},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4480054974555969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44551989436149597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35466572642326355},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3530353903770447},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33832454681396484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513177633285522},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6534995436668396},{"id":"https://openalex.org/C43122875","wikidata":"https://www.wikidata.org/wiki/Q5428522","display_name":"Facet (psychology)","level":4,"score":0.6152786016464233},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6098037362098694},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5489481091499329},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4559384882450104},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4480054974555969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44551989436149597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35466572642326355},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3530353903770447},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33832454681396484},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C187288502","wikidata":"https://www.wikidata.org/wiki/Q641118","display_name":"Personality","level":2,"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/C2865642","wikidata":"https://www.wikidata.org/wiki/Q378132","display_name":"Big Five personality traits","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1401890.1401952","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifaka.cs.uiuc.edu/~qmei2/pub/kdd08-overview.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W11540594","https://openalex.org/W1593045043","https://openalex.org/W1880262756","https://openalex.org/W1965555277","https://openalex.org/W1976719972","https://openalex.org/W1982381099","https://openalex.org/W2021314079","https://openalex.org/W2043747172","https://openalex.org/W2074449313","https://openalex.org/W2096259344","https://openalex.org/W2100858341","https://openalex.org/W2105879985","https://openalex.org/W2107743791","https://openalex.org/W2110441437","https://openalex.org/W2112247328","https://openalex.org/W2113889316","https://openalex.org/W2117853077","https://openalex.org/W2121996546","https://openalex.org/W2129294185","https://openalex.org/W2139823104","https://openalex.org/W2141631351","https://openalex.org/W2147411155","https://openalex.org/W2150461699","https://openalex.org/W2154701989","https://openalex.org/W2155225302","https://openalex.org/W2157589241","https://openalex.org/W2166900514","https://openalex.org/W2567948266","https://openalex.org/W4232023503","https://openalex.org/W4233135949","https://openalex.org/W4400191782","https://openalex.org/W7037644959"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"A":[0],"common":[1],"task":[2],"in":[3,17,123,148,219],"many":[4],"text":[5,19,167,216],"mining":[6,217],"applications":[7],"is":[8,207],"to":[9,43,130,143,157,214],"generate":[10,175],"a":[11,15,18,38,56,82,101,115,128,145,154,176],"multi-faceted":[12,146,177],"overview":[13,23,147,178],"of":[14,32,41,46,81,104,120,166],"topic":[16,140],"collection.":[20],"Such":[21,95],"an":[22,29,96,138,149],"not":[24,77],"only":[25,98],"directly":[26],"serves":[27],"as":[28,55],"informative":[30,200],"summary":[31],"the":[33,47,79,121,182],"topic,":[34],"but":[35],"also":[36,198],"provides":[37],"detailed":[39],"view":[40],"navigation":[42],"different":[44,164,220],"facets":[45,72],"topic.":[48],"Existing":[49],"work":[50],"has":[51,67],"cast":[52],"this":[53,107,159],"problem":[54,58],"categorization":[57],"and":[59,113,141],"requires":[60],"training":[61,194],"examples":[62,87],"for":[63,88,100,137,179],"each":[64,89,133],"facet.":[65],"This":[66],"three":[68],"limitations:":[69],"(1)":[70],"All":[71],"are":[73,91,185,197],"predefined,":[74],"which":[75,124],"may":[76],"fit":[78],"need":[80],"particular":[83],"user.":[84],"(2)":[85],"Training":[86],"facet":[90,134],"often":[92],"unavailable.":[93],"(3)":[94],"approach":[97,156,172],"works":[99],"predefined":[102],"type":[103],"topics.":[105],"In":[106],"paper,":[108],"we":[109,125],"break":[110],"these":[111],"limitations":[112],"study":[114],"more":[116,199],"realistic":[117],"new":[118],"setup":[119],"problem,":[122],"would":[126],"allow":[127],"user":[129],"flexibly":[131],"describe":[132],"with":[135,187,193],"keywords":[136],"arbitrary":[139,180],"attempt":[142,153],"mine":[144],"unsupervised":[150],"way.":[151],"We":[152],"probabilistic":[155],"solve":[158],"problem.":[160],"Empirical":[161],"experiments":[162],"on":[163],"genres":[165],"data":[168],"show":[169],"that":[170],"our":[171],"can":[173,211],"effectively":[174],"topics;":[181],"generated":[183,189],"overviews":[184],"comparable":[186],"those":[188],"by":[190],"supervised":[191],"methods":[192],"examples.":[195],"They":[196],"than":[201],"unstructured":[202],"flat":[203],"summaries.":[204],"The":[205],"method":[206],"quite":[208],"general,":[209],"thus":[210],"be":[212],"applied":[213],"multiple":[215],"tasks":[218],"application":[221],"domains.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}