{"id":"https://openalex.org/W2112247328","doi":"https://doi.org/10.1145/1014052.1014150","title":"A cross-collection mixture model for comparative text mining","display_name":"A cross-collection mixture model for comparative text mining","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2112247328","doi":"https://doi.org/10.1145/1014052.1014150","mag":"2112247328"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth 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/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":true,"raw_author_name":"ChengXiang Zhai","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034922152","display_name":"Atulya Velivelli","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":false,"raw_author_name":"Atulya Velivelli","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080653038","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-5425-0011"},"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":"Bei Yu","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028518494"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":15.7124,"has_fulltext":false,"cited_by_count":275,"citation_normalized_percentile":{"value":0.99017257,"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":"743","last_page":"748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980000257492065,"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":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9952999949455261,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922000169754028,"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":0.6315197348594666},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34597939252853394},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3435709774494171}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315197348594666},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34597939252853394},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3435709774494171}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1014052.1014150","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.578.7787","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.578.7787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/~velivell/ctm4.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.1120","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.1120","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/czhai/pub/sigkdd04-ctm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.6585","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.6585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://beiyu.syr.edu/KDD2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1537217019","https://openalex.org/W1880262756","https://openalex.org/W2003222605","https://openalex.org/W2034721576","https://openalex.org/W2049633694","https://openalex.org/W2064580901","https://openalex.org/W2100506586","https://openalex.org/W2101561981","https://openalex.org/W2102650424","https://openalex.org/W2107743791","https://openalex.org/W2112378479","https://openalex.org/W2121940249","https://openalex.org/W2155453030","https://openalex.org/W2979454998","https://openalex.org/W4233135949","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W3022131925","https://openalex.org/W2349174110","https://openalex.org/W1597238586","https://openalex.org/W1536405386","https://openalex.org/W2326857978","https://openalex.org/W1990780094"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,13],"define":[4],"and":[5,49,73,98,101,140,146,177],"study":[6],"a":[7,21,78,83,135,141,150,157],"novel":[8],"text":[9,18,25,31,90,111,131],"mining":[10,32],"prob-lem,":[11],"which":[12],"refer":[14],"to":[15,34,105],"as":[16,43,45],"comparative":[17,30,89],"mining.":[19,91],"Given":[20],"set":[22,108,139],"of":[23,29,51,70,109],"comparable":[24],"collections,":[26],"the":[27,47,120,126,164,171],"task":[28],"is":[33,166],"discover":[35],"any":[36],"latent":[37,172],"common":[38,56,79,173],"themes":[39,174],"across":[40,175],"all":[41],"collections":[42,53,176],"well":[44],"summarize":[46],"similarity":[48],"differ-ences":[50],"these":[52],"along":[54],"each":[55],"theme.":[57],"This":[58],"general":[59],"problem":[60],"subsumes":[61],"many":[62],"interesting":[63],"applications,":[64],"in-cluding":[65],"business":[66],"intelligence,":[67],"summarizing":[68],"reviews":[69],"similar":[71],"products,":[72],"comparing":[74],"different":[75,130],"opinions":[76],"about":[77],"topic.":[80],"We":[81,124],"propose":[82],"generative":[84],"probabilistic":[85],"mixture":[86,158,184],"model":[87,93,114,127,165],"for":[88],"The":[92,113],"simultaneously":[94],"per-forms":[95],"cross-collection":[96],"clustering":[97,152],"within-collection":[99],"clus-tering,":[100],"can":[102,115],"be":[103,116],"applied":[104],"an":[106],"arbitrary":[107],"compara-ble":[110],"collections.":[112],"estimated":[117],"efficiently":[118],"using":[119],"Expectation-Maximization":[121],"(EM)":[122],"algorithm.":[123],"evaluate":[125],"on":[128,156],"two":[129],"data":[132,138,144],"sets":[133],"(i.e.,":[134],"news":[136],"article":[137],"laptop":[142],"review":[143],"set),":[145],"compare":[147],"it":[148],"with":[149],"baseline":[151,183],"method":[153],"also":[154],"based":[155],"model.":[159,185],"Experiment":[160],"results":[161],"show":[162],"that":[163],"quite":[167],"effective":[168],"in":[169],"discovering":[170],"performs":[178],"significantly":[179],"better":[180],"than":[181],"our":[182],"1.":[186]},"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":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":41},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}