{"id":"https://openalex.org/W2163021329","doi":"https://doi.org/10.1145/1835804.1835890","title":"Topic models with power-law using Pitman-Yor process","display_name":"Topic models with power-law using Pitman-Yor process","publication_year":2010,"publication_date":"2010-07-25","ids":{"openalex":"https://openalex.org/W2163021329","doi":"https://doi.org/10.1145/1835804.1835890","mag":"2163021329"},"language":"en","primary_location":{"id":"doi:10.1145/1835804.1835890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060421432","display_name":"Issei Sato","orcid":"https://orcid.org/0000-0002-5066-1435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Issei Sato","raw_affiliation_strings":["Tokyo University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["Tokyo University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"673","last_page":"682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9993000030517578,"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":0.9993000030517578,"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/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"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":0.9312126636505127},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6918590068817139},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6647350192070007},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5968669056892395},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.5650409460067749},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.5423673987388611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5381748080253601},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.43086421489715576},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4145546555519104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3604002594947815},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.33733487129211426},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.32257723808288574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.316265732049942},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27350255846977234},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.18668311834335327}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9312126636505127},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6918590068817139},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6647350192070007},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5968669056892395},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.5650409460067749},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.5423673987388611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5381748080253601},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.43086421489715576},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4145546555519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3604002594947815},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33733487129211426},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32257723808288574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.316265732049942},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27350255846977234},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.18668311834335327},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1835804.1835890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835804.1835890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.4256","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.4256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.r.dl.itc.u-tokyo.ac.jp/~nakagawa/academic-res/SIGKDD2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W159230833","https://openalex.org/W190008395","https://openalex.org/W263845233","https://openalex.org/W1498269992","https://openalex.org/W1575299154","https://openalex.org/W1712618182","https://openalex.org/W1880262756","https://openalex.org/W1915315806","https://openalex.org/W1947594277","https://openalex.org/W1985615910","https://openalex.org/W2001082470","https://openalex.org/W2005902041","https://openalex.org/W2045007904","https://openalex.org/W2069429561","https://openalex.org/W2072644219","https://openalex.org/W2087309226","https://openalex.org/W2091797506","https://openalex.org/W2098401485","https://openalex.org/W2107743791","https://openalex.org/W2109154616","https://openalex.org/W2112050062","https://openalex.org/W2112971401","https://openalex.org/W2140124448","https://openalex.org/W2140991203","https://openalex.org/W2154099718","https://openalex.org/W2154292407","https://openalex.org/W2159399018","https://openalex.org/W2165636119","https://openalex.org/W2169470026","https://openalex.org/W2595697910","https://openalex.org/W2963683999","https://openalex.org/W2990138404","https://openalex.org/W4233135949","https://openalex.org/W6607826182","https://openalex.org/W6629892778","https://openalex.org/W6637242313","https://openalex.org/W6637370413","https://openalex.org/W6640120797","https://openalex.org/W6676893574","https://openalex.org/W6682718134"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W4294769427","https://openalex.org/W1895908943","https://openalex.org/W4206967254","https://openalex.org/W4293734197","https://openalex.org/W2761847515","https://openalex.org/W130869231","https://openalex.org/W2131689821","https://openalex.org/W2250993361","https://openalex.org/W2053306114"],"abstract_inverted_index":{"One":[0],"important":[1],"approach":[2],"for":[3],"knowledge":[4],"discovery":[5],"and":[6,78,203],"data":[7],"mining":[8],"is":[9,71,89,166],"to":[10,123],"estimate":[11],"unobserved":[12],"variables":[13,16],"because":[14],"latent":[15,26,38,49,80,102,114,118],"can":[17,44],"indicate":[18],"hidden":[19],"specific":[20],"properties":[21,195],"of":[22,42,63,69,105,161,196,206,224],"observed":[23],"data.":[24],"The":[25,189],"factor":[27,81],"model":[28,95,179,192,216],"assumes":[29,112],"that":[30,66,113],"each":[31],"item":[32,74],"in":[33,171,219,222],"a":[34,37,54,57,61,76,79,83,90,106,124,138,143,162,176,197,199],"record":[35,55],"has":[36],"factor;":[39],"the":[40,67,97,101,132,149,158,181,185,204],"co-occurrence":[41],"items":[43],"then":[45],"be":[46],"modeled":[47],"by":[48,141],"factors.":[50],"In":[51,209],"document":[52,58,107,220],"modeling,":[53],"indicates":[56,75,82],"represented":[59],"as":[60,168],"\"bag":[62],"words,\"":[64],"meaning":[65],"order":[68],"words":[70],"ignored,":[72],"an":[73,210],"word":[77,139,163,201],"topic.":[84],"Latent":[85],"Dirichlet":[86,98,133,150],"allocation":[87],"(LDA)":[88],"widely":[91],"used":[92],"Bayesian":[93],"topic":[94,103,178,187,191],"applying":[96],"distribution":[99,104,126,140,145,202],"over":[100],"having":[108],"multiple":[109,207],"topics.":[110,208],"LDA":[111,135,218],"topics,":[115],"i.e.,":[116],"discrete":[117],"variables,":[119],"are":[120,129],"distributed":[121],"according":[122],"multinomial":[125,144],"whose":[127,146],"parameters":[128,147],"generated":[130],"from":[131],"distribution.":[134,151],"also":[136],"models":[137],"using":[142,180,212],"follows":[148],"This":[152],"Dirichlet-multinomial":[153],"setting,":[154],"however,":[155],"cannot":[156],"capture":[157],"power-law":[159,200],"phenomenon":[160],"distribution,":[164],"which":[165],"known":[167],"Zipf's":[169],"law":[170],"linguistics.":[172],"We":[173],"therefore":[174],"propose":[175],"novel":[177],"Pitman-Yor(PY)":[182],"process,":[183],"called":[184],"PY":[186,190],"model.":[188],"captures":[193],"two":[194],"document;":[198],"presence":[205],"experiment":[211],"real":[213],"data,":[214],"this":[215],"outperformed":[217],"modeling":[221],"terms":[223],"perplexity.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}