{"id":"https://openalex.org/W1995866178","doi":"https://doi.org/10.1145/2623330.2623622","title":"Mining topics in documents","display_name":"Mining topics in documents","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W1995866178","doi":"https://doi.org/10.1145/2623330.2623622","mag":"1995866178"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623622","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 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/A5100438515","display_name":"Zhiyuan Chen","orcid":"https://orcid.org/0000-0002-6984-7248"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyuan Chen","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339927","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-4096-6980"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bing Liu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100438515"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":33.9478,"has_fulltext":false,"cited_by_count":164,"citation_normalized_percentile":{"value":0.99766911,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1116","last_page":"1125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9961000084877014,"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":0.8297899961471558},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7177923917770386},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.5812499523162842},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5788211226463318},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5349593758583069},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5241832137107849},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5070672035217285},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4888724684715271},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.46392473578453064},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.43113434314727783},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42199721932411194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.375785231590271},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3441876769065857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297899961471558},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7177923917770386},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.5812499523162842},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5788211226463318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5349593758583069},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5241832137107849},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5070672035217285},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4888724684715271},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.46392473578453064},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.43113434314727783},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42199721932411194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375785231590271},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3441876769065857},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2623330.2623622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623622","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 SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G140967883","display_name":null,"funder_award_id":"no. IIS-1111092","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W7939015","https://openalex.org/W192837634","https://openalex.org/W1506246224","https://openalex.org/W1532908297","https://openalex.org/W1576326591","https://openalex.org/W1608334810","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1969486090","https://openalex.org/W2000106226","https://openalex.org/W2016196732","https://openalex.org/W2037959956","https://openalex.org/W2044185127","https://openalex.org/W2044429219","https://openalex.org/W2068463433","https://openalex.org/W2096110600","https://openalex.org/W2098062695","https://openalex.org/W2106035193","https://openalex.org/W2108646579","https://openalex.org/W2120501001","https://openalex.org/W2126204609","https://openalex.org/W2128507180","https://openalex.org/W2129294185","https://openalex.org/W2129604374","https://openalex.org/W2130339025","https://openalex.org/W2145768976","https://openalex.org/W2157589241","https://openalex.org/W2158085718","https://openalex.org/W2159426623","https://openalex.org/W2160409620","https://openalex.org/W2160660844","https://openalex.org/W2165698076","https://openalex.org/W2169289922","https://openalex.org/W2250585720","https://openalex.org/W2252012216","https://openalex.org/W2364964713","https://openalex.org/W2612769033","https://openalex.org/W2951947127","https://openalex.org/W2964048480"],"related_works":["https://openalex.org/W2379908271","https://openalex.org/W2385621242","https://openalex.org/W2367629516","https://openalex.org/W2086580554","https://openalex.org/W2553860513","https://openalex.org/W1986001501","https://openalex.org/W2353740909","https://openalex.org/W4318719391","https://openalex.org/W2475408106","https://openalex.org/W2592721119"],"abstract_inverted_index":{"Topic":[0],"modeling":[1,17],"has":[2],"been":[3,90],"widely":[4],"used":[5],"to":[6,31,35,96,102,106,119,135,161,166],"mine":[7,147],"topics":[8],"from":[9,152,239],"documents.":[10,50],"However,":[11,39],"a":[12,22,52,68,113,142],"key":[13],"weakness":[14],"of":[15,25,29,55,71,75,176,191,223],"topic":[16,59,76,87],"is":[18,173],"that":[19,195,207,244],"it":[20,160],"needs":[21],"large":[23,69],"amount":[24],"data":[26,179],"(e.g.,":[27],"thousands":[28],"documents)":[30],"provide":[32,97],"reliable":[33,149],"statistics":[34],"generate":[36,167],"coherent":[37,169],"topics.":[38,65,109,170],"in":[40,129,200,213],"practice,":[41],"many":[42,49],"document":[43],"collections":[44],"do":[45],"not":[46,211],"have":[47,89],"so":[48],"Given":[51],"small":[53],"number":[54],"documents,":[56],"the":[57,104,126,130,153,163,177,183,201,214,224,245],"classic":[58],"model":[60,105,164],"LDA":[61],"generates":[62],"very":[63],"poor":[64],"Even":[66],"with":[67,141,220],"volume":[70],"data,":[72],"unsupervised":[73],"learning":[74],"models":[77,88],"can":[78],"still":[79],"produce":[80,107],"unsatisfactory":[81],"results.":[82],"In":[83],"recently":[84],"years,":[85],"knowledge-based":[86],"proposed,":[91],"which":[92],"ask":[93],"human":[94],"users":[95],"some":[98,148],"prior":[99],"domain":[100],"knowledge":[101,151,230,232],"guide":[103,162],"better":[108],"Our":[110],"research":[111],"takes":[112],"radically":[114],"different":[115],"approach.":[116],"We":[117],"propose":[118],"learn":[120],"as":[121],"humans":[122],"do,":[123],"i.e.,":[124,228],"retaining":[125],"results":[127,156,235],"learned":[128],"past":[131,154],"and":[132,157,204,231],"using":[133,236],"them":[134],"help":[136],"future":[137],"learning.":[138],"When":[139],"faced":[140],"new":[143],"task,":[144],"we":[145],"first":[146],"(prior)":[150],"learning/modeling":[155],"then":[158],"use":[159],"inference":[165],"more":[168],"This":[171],"approach":[172,247],"possible":[174],"because":[175],"big":[178],"readily":[180],"available":[181],"on":[182],"Web.":[184],"The":[185],"proposed":[186,246],"algorithm":[187],"mines":[188],"two":[189,196,208,221],"forms":[190],"knowledge:":[192],"must-link":[193],"(meaning":[194,206],"words":[197,209],"should":[198,210],"be":[199,212],"same":[202,215],"topic)":[203],"cannot-link":[205],"topic).":[216],"It":[217],"also":[218],"deals":[219],"problems":[222],"automatically":[225],"mined":[226],"knowledge,":[227],"wrong":[229],"transitivity.":[233],"Experimental":[234],"review":[237],"documents":[238],"100":[240],"product":[241],"domains":[242],"show":[243],"makes":[248],"dramatic":[249],"improvements":[250],"over":[251],"state-of-the-art":[252],"baselines.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":30},{"year":2015,"cited_by_count":26}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}