{"id":"https://openalex.org/W2109154616","doi":"https://doi.org/10.1145/1014052.1014087","title":"Probabilistic author-topic models for information discovery","display_name":"Probabilistic author-topic models for information discovery","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2109154616","doi":"https://doi.org/10.1145/1014052.1014087","mag":"2109154616"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014087","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/A5051768325","display_name":"Mark Steyvers","orcid":"https://orcid.org/0000-0003-1466-5647"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Steyvers","raw_affiliation_strings":["University of California - Irvine, Irvine, CA"],"affiliations":[{"raw_affiliation_string":"University of California - Irvine, Irvine, CA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077460655","display_name":"Padhraic Smyth","orcid":"https://orcid.org/0000-0001-9971-8378"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Padhraic Smyth","raw_affiliation_strings":["University of California - Irvine, Irvine, CA"],"affiliations":[{"raw_affiliation_string":"University of California - Irvine, Irvine, CA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003092468","display_name":"Michal Rosen\u2010Zvi","orcid":"https://orcid.org/0000-0001-7616-9724"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Rosen-Zvi","raw_affiliation_strings":["University of California - Irvine, Irvine, CA"],"affiliations":[{"raw_affiliation_string":"University of California - Irvine, Irvine, CA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077079119","display_name":"Thomas L. Griffiths","orcid":"https://orcid.org/0000-0002-5138-7255"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Griffiths","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051768325"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":18.4851,"has_fulltext":false,"cited_by_count":581,"citation_normalized_percentile":{"value":0.99257019,"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":"306","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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":0.8343179225921631},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6934984922409058},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6753285527229309},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5320217609405518},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5156751871109009},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5120709538459778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4953059256076813},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4479962885379791},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4387741684913635},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.43500077724456787},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4285210967063904},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08174780011177063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343179225921631},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6934984922409058},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6753285527229309},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5320217609405518},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5156751871109009},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5120709538459778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4953059256076813},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4479962885379791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4387741684913635},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.43500077724456787},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4285210967063904},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08174780011177063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1014052.1014087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014087","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:10.1.1.10.2031","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.2031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://psiexp.ss.uci.edu/research/papers/author_topics_kdd.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.2369","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.2369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~smyth/kddpapers/author_topics.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.374.8657","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.374.8657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/kdd04/docs/p306.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.7012","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.datalab.uci.edu/papers/author-topics-kdd04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1547032355","https://openalex.org/W1606247040","https://openalex.org/W1669437150","https://openalex.org/W1788071186","https://openalex.org/W1880262756","https://openalex.org/W1978558026","https://openalex.org/W1996764654","https://openalex.org/W2001082470","https://openalex.org/W2019048419","https://openalex.org/W2025572017","https://openalex.org/W2036216970","https://openalex.org/W2069976569","https://openalex.org/W2107743791","https://openalex.org/W2108346334","https://openalex.org/W2114535528","https://openalex.org/W2118537526","https://openalex.org/W2118668678","https://openalex.org/W2129936978","https://openalex.org/W2140124448","https://openalex.org/W2144270983","https://openalex.org/W2145677303","https://openalex.org/W2147152072","https://openalex.org/W2154498027","https://openalex.org/W2155048531","https://openalex.org/W2169602585","https://openalex.org/W4233135949","https://openalex.org/W4237482456","https://openalex.org/W4241122026","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2502722637","https://openalex.org/W2167662847","https://openalex.org/W1551406738","https://openalex.org/W2369308426","https://openalex.org/W2293457016","https://openalex.org/W2977842567","https://openalex.org/W1590308178","https://openalex.org/W2789919619","https://openalex.org/W1818857488","https://openalex.org/W2020540721"],"abstract_inverted_index":{"We":[0,14,91,118],"propose":[1],"a":[2,23,32,43,54,64,85,96,113],"new":[3],"unsupervised":[4,82],"learning":[5],"technique":[6],"for":[7,48,189],"extracting":[8],"information":[9],"from":[10,78,105],"large":[11,97],"text":[12],"collections.":[13],"model":[15,114,178],"documents":[16],"as":[17,42,192],"if":[18],"they":[19],"were":[20],"generated":[21],"by":[22,31,128,140,144,160,169],"two-stage":[24],"stochastic":[25],"process.":[26],"Each":[27],"author":[28,135],"is":[29,40,179],"represented":[30,41],"probability":[33,44],"distribution":[34,45],"over":[35,46],"topics,":[36],"and":[37,73,102,111,134,142,155,162,164],"each":[38,67],"topic":[39,69,133,141],"words":[47,52],"that":[49,182],"topic.":[50],"The":[51,71],"in":[53,80,120,148],"multi-author":[55],"paper":[56],"are":[57,76],"assumed":[58],"to":[59,95,176],"be":[60],"the":[61,93,106,122,125,129,149,177],"result":[62],"of":[63,66,99,124,138,158,166,186],"mixture":[65],"authors'":[68],"mixture.":[70],"topic-word":[72],"author-topic":[74,187],"distributions":[75],"learned":[77],"data":[79],"an":[81],"manner":[83],"using":[84],"Markov":[86],"chain":[87],"Monte":[88],"Carlo":[89],"algorithm.":[90],"apply":[92],"methodology":[94],"corpus":[98],"160,000":[100],"abstracts":[101,159],"85,000":[103],"authors":[104,139,163],"well-known":[107],"CiteSeer":[108],"digital":[109],"library,":[110],"learn":[112],"with":[115],"300":[116],"topics.":[117],"discuss":[119],"detail":[121],"interpretation":[123],"results":[126],"discovered":[127],"system":[130],"including":[131],"specific":[132,170],"models,":[136],"ranking":[137],"topics":[143,161],"author,":[145],"significant":[146],"trends":[147],"computer":[150],"science":[151],"literature":[152],"between":[153],"1990":[154],"2002,":[156],"parsing":[157],"detection":[165],"unusual":[167],"papers":[168],"authors.":[171],"An":[172],"online":[173],"query":[174],"interface":[175],"also":[180],"discussed":[181],"allows":[183],"interactive":[184],"exploration":[185],"models":[188],"corpora":[190],"such":[191],"CiteSeer.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":47},{"year":2014,"cited_by_count":55},{"year":2013,"cited_by_count":36},{"year":2012,"cited_by_count":54}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}