{"id":"https://openalex.org/W3205960700","doi":"https://doi.org/10.1080/01621459.2022.2089574","title":"Learning Topic Models: Identifiability and Finite-Sample Analysis","display_name":"Learning Topic Models: Identifiability and Finite-Sample Analysis","publication_year":2022,"publication_date":"2022-06-15","ids":{"openalex":"https://openalex.org/W3205960700","doi":"https://doi.org/10.1080/01621459.2022.2089574","mag":"3205960700"},"language":"en","primary_location":{"id":"doi:10.1080/01621459.2022.2089574","doi":"https://doi.org/10.1080/01621459.2022.2089574","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01621459.2022.2089574","pdf_url":null,"source":{"id":"https://openalex.org/S4394736638","display_name":"Journal of the American Statistical Association","issn_l":"0162-1459","issn":["0162-1459","1537-274X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","cwts-core","doyens","jufo-3","ki-jl-3","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Statistical Association","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/dataset/Learning_Topic_Models_Identifiability_and_Finite-Sample_Analysis/20073585","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034578500","display_name":"Yinyin Chen","orcid":"https://orcid.org/0000-0002-1192-671X","observed_orcids":["https://orcid.org/0000-0002-1192-671X"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinyin Chen","raw_affiliation_strings":["Meta Platforms, Inc., Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms, Inc., Menlo Park, CA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091777096","display_name":"Shishuang He","orcid":"https://orcid.org/0009-0008-5961-8901","observed_orcids":["https://orcid.org/0009-0008-5961-8901"]},"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":"Shishuang He","raw_affiliation_strings":["Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104208065","display_name":"Yun Yang","orcid":"https://orcid.org/0000-0002-4523-5829","observed_orcids":["https://orcid.org/0000-0002-4523-5829"]},"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":"Yun Yang","raw_affiliation_strings":["Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071868053","display_name":"Feng Liang","orcid":"https://orcid.org/0000-0002-4173-3003","observed_orcids":["https://orcid.org/0000-0002-4173-3003"]},"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":"Feng Liang","raw_affiliation_strings":["Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071868053"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.572,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64110534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"118","issue":"544","first_page":"2860","last_page":"2875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7271000146865845,"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":0.7271000146865845,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.19200000166893005,"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":0.0640999972820282,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/topic-modeling","display_name":"topic modeling","score":0.9850000143051147},{"id":"https://openalex.org/keywords/identifiability","display_name":"identifiability","score":0.7760000228881836},{"id":"https://openalex.org/keywords/maximum-likelihood-estimation","display_name":"maximum likelihood estimation","score":0.9070000052452087},{"id":"https://openalex.org/keywords/marginal-likelihood","display_name":"marginal likelihood","score":0.9950000047683716},{"id":"https://openalex.org/keywords/volume-minimization","display_name":"volume minimization","score":0.984000027179718},{"id":"https://openalex.org/keywords/separability-criterion","display_name":"separability criteria","score":0.7120000123977661},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.5429999828338623},{"id":"https://openalex.org/keywords/latent-structure-learning","display_name":"latent structure learning","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.9320093393325806},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7380961179733276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789062023162842},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6108869910240173},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5150313377380371},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.509863555431366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4987609386444092},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.43267661333084106},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4129323661327362},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35885339975357056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27337923645973206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19106736779212952},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1080/01621459.2022.2089574","doi":"https://doi.org/10.1080/01621459.2022.2089574","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01621459.2022.2089574","pdf_url":null,"source":{"id":"https://openalex.org/S4394736638","display_name":"Journal of the American Statistical Association","issn_l":"0162-1459","issn":["0162-1459","1537-274X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","cwts-core","doyens","jufo-3","ki-jl-3","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Statistical Association","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:taf:jnlasa:v:118:y:2023:i:544:p:2860-2875","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1080/01621459.2022.2089574","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:figshare.com:article/20073585","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Learning_Topic_Models_Identifiability_and_Finite-Sample_Analysis/20073585","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"doi:10.6084/m9.figshare.20073585.v1","doi":"https://doi.org/10.6084/m9.figshare.20073585.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.20073585.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20073585","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Learning_Topic_Models_Identifiability_and_Finite-Sample_Analysis/20073585","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.7200000286102295}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W159693449","https://openalex.org/W1585365342","https://openalex.org/W1605711022","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1882879704","https://openalex.org/W1970136394","https://openalex.org/W1970377488","https://openalex.org/W1990516625","https://openalex.org/W1994210570","https://openalex.org/W1999617067","https://openalex.org/W2001082470","https://openalex.org/W2021680564","https://openalex.org/W2041701373","https://openalex.org/W2063392856","https://openalex.org/W2070135644","https://openalex.org/W2072477463","https://openalex.org/W2073414385","https://openalex.org/W2083904924","https://openalex.org/W2101837437","https://openalex.org/W2105617746","https://openalex.org/W2105724942","https://openalex.org/W2114486983","https://openalex.org/W2116403087","https://openalex.org/W2117986441","https://openalex.org/W2118943995","https://openalex.org/W2125477383","https://openalex.org/W2125510930","https://openalex.org/W2128521126","https://openalex.org/W2129062845","https://openalex.org/W2140318696","https://openalex.org/W2149655761","https://openalex.org/W2157321686","https://openalex.org/W2290915992","https://openalex.org/W2294384375","https://openalex.org/W2296319761","https://openalex.org/W2533991995","https://openalex.org/W2545506142","https://openalex.org/W2554348171","https://openalex.org/W2556090297","https://openalex.org/W2604272474","https://openalex.org/W2610097833","https://openalex.org/W2785015228","https://openalex.org/W2900144602","https://openalex.org/W2921008552","https://openalex.org/W2950143340","https://openalex.org/W2952362964","https://openalex.org/W2962790067","https://openalex.org/W2963625764","https://openalex.org/W2963884903","https://openalex.org/W2964215670","https://openalex.org/W2964350306","https://openalex.org/W2970888656","https://openalex.org/W3103438822","https://openalex.org/W3155503733","https://openalex.org/W4237791300","https://openalex.org/W4289303772","https://openalex.org/W4302023333","https://openalex.org/W6636440780","https://openalex.org/W6677605506","https://openalex.org/W6678900246","https://openalex.org/W6737110777","https://openalex.org/W6759977971"],"related_works":["https://openalex.org/W2724847603","https://openalex.org/W2034041141","https://openalex.org/W2184661725","https://openalex.org/W2900187352","https://openalex.org/W2573470972","https://openalex.org/W2105626102","https://openalex.org/W2131038454","https://openalex.org/W3131140146","https://openalex.org/W2794773137","https://openalex.org/W2768373660"],"abstract_inverted_index":{"Topic":[0],"models":[1],"provide":[2],"a":[3,19,34,53,63,83,118],"useful":[4],"text-mining":[5],"tool":[6],"for":[7,26,89,131,159],"learning,":[8],"extracting,":[9],"and":[10,42,120,135,141,154],"discovering":[11],"latent":[12,45,59],"structures":[13],"in":[14,30,74],"large":[15],"text":[16],"corpora.":[17],"Although":[18],"plethora":[20],"of":[21,38,44,58,77,86,107,112,143],"methods":[22],"have":[23],"been":[24],"proposed":[25,133],"topic":[27,46,90,109],"modeling,":[28],"lacking":[29],"the":[31,39,72,105,132],"literature":[32],"is":[33,68],"formal":[35],"theoretical":[36],"investigation":[37],"statistical":[40],"identifiability":[41],"accuracy":[43],"estimation.":[47],"In":[48],"this":[49,160],"article,":[50],"we":[51],"propose":[52],"maximum":[54],"likelihood":[55,66],"estimator":[56,134],"(MLE)":[57],"topics":[60],"based":[61],"on":[62,104],"specific":[64],"integrated":[65],"that":[67,94],"naturally":[69],"connected":[70],"to":[71],"concept,":[73],"computational":[75],"geometry,":[76],"volume":[78],"minimization.":[79],"Our":[80],"theory":[81],"introduces":[82],"new":[84],"set":[85],"geometric":[87],"conditions":[88,93,116],"model":[91],"identifiability,":[92],"are":[95,162],"weaker":[96],"than":[97],"conventional":[98],"separability":[99],"conditions,":[100],"which":[101],"typically":[102],"rely":[103],"existence":[106],"pure":[108],"documents":[110],"or":[111],"anchor":[113],"words.":[114],"Weaker":[115],"allow":[117],"wider":[119],"thus":[121],"potentially":[122],"more":[123],"fruitful":[124],"investigation.":[125],"We":[126,146],"conduct":[127],"finite-sample":[128],"error":[129],"analysis":[130],"discuss":[136],"connections":[137],"between":[138],"our":[139],"results":[140],"those":[142],"previous":[144],"investigations.":[145],"conclude":[147],"with":[148],"empirical":[149],"studies":[150],"employing":[151],"both":[152],"simulated":[153],"real":[155],"datasets.":[156],"Supplementary":[157],"materials":[158],"article":[161],"available":[163],"online.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}