{"id":"https://openalex.org/W2001975024","doi":"https://doi.org/10.1145/2487575.2487697","title":"Stochastic collapsed variational Bayesian inference for latent Dirichlet allocation","display_name":"Stochastic collapsed variational Bayesian inference for latent Dirichlet allocation","publication_year":2013,"publication_date":"2013-08-11","ids":{"openalex":"https://openalex.org/W2001975024","doi":"https://doi.org/10.1145/2487575.2487697","mag":"2001975024"},"language":"en","primary_location":{"id":"doi:10.1145/2487575.2487697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2487697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th 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/A5010326834","display_name":"James R. Foulds","orcid":"https://orcid.org/0000-0003-0935-4182"},"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":"James Foulds","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014330481","display_name":"Levi Boyles","orcid":null},"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":"Levi Boyles","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064602468","display_name":"Christopher DuBois","orcid":null},"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":"Christopher DuBois","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","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, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087368991","display_name":"Max Welling","orcid":"https://orcid.org/0000-0003-1484-2121"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Max Welling","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands","university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]},{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010326834"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":23.9118,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.99506553,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9983999729156494,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9983999729156494,"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":0.9980999827384949,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9944000244140625,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9294716119766235},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7790113687515259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7529605627059937},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7467050552368164},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.63629150390625},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5431200265884399},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5361853241920471},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5115448236465454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48625075817108154},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.47287601232528687},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4560546576976776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42346012592315674},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3637464642524719},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32489877939224243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1591511368751526}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9294716119766235},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7790113687515259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7529605627059937},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7467050552368164},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.63629150390625},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5431200265884399},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5361853241920471},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5115448236465454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48625075817108154},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.47287601232528687},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4560546576976776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42346012592315674},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3637464642524719},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32489877939224243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1591511368751526},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2487575.2487697","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2487697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/c4b93756-4632-403b-a130-510312c4c850","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/stochastic-collapsed-variational-bayesian-inference-for-latent-dirichlet-allocation(c4b93756-4632-403b-a130-510312c4c850).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foulds, J, Boyles, L, DuBois, C, Smyth, P & Welling, M 2013, Stochastic Collapsed Variational Bayesian Inference for Latent Dirichlet Allocation. in I S Dhillon, Y Koren, R Ghani, T E Senator, P Bradley, R Parekh, J He, R L Grossman & R Uthurusamy (eds), KDD '13: the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 11-14, 2013, Chicago, Illinois, USA. New York, pp. 446-454, Conference on Knowledge Discovery and Data Mining (KDD), 11/08/13. https://doi.org/10.1145/2487575.2487697","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/c4b93756-4632-403b-a130-510312c4c850","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/stochastic-collapsed-variational-bayesian-inference-for-latent-dirichlet-allocation(c4b93756-4632-403b-a130-510312c4c850).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Foulds, J, Boyles, L, DuBois, C, Smyth, P & Welling, M 2013, Stochastic Collapsed Variational Bayesian Inference for Latent Dirichlet Allocation. in I S Dhillon, Y Koren, R Ghani, T E Senator, P Bradley, R Parekh, J He, R L Grossman & R Uthurusamy (eds), KDD '13: the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: August 11-14, 2013, Chicago, Illinois, USA. New York, pp. 446-454, Conference on Knowledge Discovery and Data Mining (KDD), 11/08/13. https://doi.org/10.1145/2487575.2487697","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W316065036","https://openalex.org/W1526533144","https://openalex.org/W1542680845","https://openalex.org/W1686266550","https://openalex.org/W1880262756","https://openalex.org/W1994616650","https://openalex.org/W2001082470","https://openalex.org/W2022638422","https://openalex.org/W2027791497","https://openalex.org/W2041517243","https://openalex.org/W2054333436","https://openalex.org/W2116137244","https://openalex.org/W2130428211","https://openalex.org/W2133555934","https://openalex.org/W2141056424","https://openalex.org/W2146341620","https://openalex.org/W2150731624","https://openalex.org/W2157991246","https://openalex.org/W2158266063","https://openalex.org/W2159426623","https://openalex.org/W2161353674","https://openalex.org/W2165599843","https://openalex.org/W2165693128","https://openalex.org/W2166851633","https://openalex.org/W2171278750","https://openalex.org/W2950770596","https://openalex.org/W3003241580","https://openalex.org/W3105418769","https://openalex.org/W4250619709","https://openalex.org/W6632241081","https://openalex.org/W6683847445","https://openalex.org/W6684489972","https://openalex.org/W6786594163"],"related_works":["https://openalex.org/W2497860580","https://openalex.org/W2097627380","https://openalex.org/W2914864478","https://openalex.org/W2891616219","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W3204672119","https://openalex.org/W22044811","https://openalex.org/W2625329765"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"an":[3],"explosion":[4],"in":[5,13,30,126,137],"the":[6,62,66,87,90,99,120,132],"amount":[7],"of":[8,19,61,65,89,134],"digital":[9],"text":[10,97],"information":[11],"available":[12],"recent":[14],"years,":[15],"leading":[16],"to":[17,44,103,108],"challenges":[18],"scale":[20],"for":[21,25,35,73,78],"traditional":[22],"inference":[23,33,77],"algorithms":[24,34],"topic":[26,46,135],"models.":[27],"Recent":[28],"advances":[29],"stochastic":[31,71],"variational":[32,75],"latent":[36],"Dirichlet":[37],"allocation":[38],"(LDA)":[39],"have":[40],"made":[41],"it":[42],"feasible":[43],"learn":[45,123],"models":[47,136],"on":[48,95,128],"very":[49],"large-scale":[50,96],"corpora,":[51,98,130],"but":[52],"these":[53],"methods":[54],"do":[55],"not":[56],"currently":[57],"take":[58],"full":[59],"advantage":[60],"collapsed":[63,74],"representation":[64],"model.":[67],"We":[68],"propose":[69],"a":[70,109],"algorithm":[72,100],"Bayesian":[76],"LDA,":[79],"which":[80],"is":[81],"simpler":[82],"and":[83,106],"more":[84],"efficient":[85],"than":[86,112],"state":[88],"art":[91],"method.":[92],"In":[93],"experiments":[94,116],"was":[101],"found":[102],"converge":[104],"faster":[105],"often":[107],"better":[110],"solution":[111],"previous":[113],"methods.":[114],"Human-subject":[115],"also":[117],"demonstrated":[118],"that":[119],"method":[121],"can":[122],"coherent":[124],"topics":[125],"seconds":[127],"small":[129],"facilitating":[131],"use":[133],"interactive":[138],"document":[139],"analysis":[140],"software.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}