{"id":"https://openalex.org/W2067818150","doi":"https://doi.org/10.1145/1401890.1401975","title":"Model-based document clustering with a collapsed gibbs sampler","display_name":"Model-based document clustering with a collapsed gibbs sampler","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2067818150","doi":"https://doi.org/10.1145/1401890.1401975","mag":"2067818150"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th 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/A5013219521","display_name":"Daniel D. Walker","orcid":"https://orcid.org/0000-0002-4348-1233"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel David Walker","raw_affiliation_strings":["Brigham Young University, Provo, UT, USA"],"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090791372","display_name":"Eric K. Ringger","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric K. Ringger","raw_affiliation_strings":["Brigham Young University, Probo, UT, USA"],"affiliations":[{"raw_affiliation_string":"Brigham Young University, Probo, UT, USA","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013219521"],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":5.7205,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95649064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9991999864578247,"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":0.9991999864578247,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9919999837875366,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8084455728530884},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.803108811378479},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7872371673583984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7149935364723206},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5548876523971558},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5141142010688782},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.47290074825286865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3661358952522278},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33017271757125854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3296009302139282},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.078971266746521}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8084455728530884},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.803108811378479},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7872371673583984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149935364723206},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5548876523971558},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5141142010688782},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47290074825286865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3661358952522278},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33017271757125854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296009302139282},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.078971266746521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W128638292","https://openalex.org/W316065036","https://openalex.org/W1651093245","https://openalex.org/W1745685099","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2024315245","https://openalex.org/W2038885294","https://openalex.org/W2045656233","https://openalex.org/W2080972498","https://openalex.org/W2087101057","https://openalex.org/W2094414211","https://openalex.org/W2096152098","https://openalex.org/W2096878708","https://openalex.org/W2099064293","https://openalex.org/W2109450366","https://openalex.org/W2121853761","https://openalex.org/W2127042504","https://openalex.org/W2130428211","https://openalex.org/W2138615112","https://openalex.org/W2147706904","https://openalex.org/W2157305458","https://openalex.org/W2541688157","https://openalex.org/W2595697910","https://openalex.org/W2963673689","https://openalex.org/W4232383088","https://openalex.org/W4235169531","https://openalex.org/W4250619709","https://openalex.org/W4251644969"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"Model-based":[0],"algorithms":[1],"are":[2],"emerging":[3],"as":[4,17],"a":[5,67,71],"preferred":[6],"method":[7],"for":[8,24,35,44,63],"document":[9,47,64],"clustering.":[10,48],"As":[11],"computing":[12],"resources":[13],"improve,":[14],"methods":[15,81],"such":[16],"Gibbs":[18,30],"sampling":[19,31],"have":[20],"become":[21],"more":[22],"common":[23],"parameter":[25],"estimation":[26],"in":[27,46],"these":[28],"models.":[29],"is":[32],"well":[33],"understood":[34],"many":[36],"applications,":[37],"but":[38],"has":[39],"not":[40],"been":[41],"extensively":[42],"studied":[43],"use":[45],"We":[49],"explore":[50],"the":[51,54,97],"convergence":[52],"rate,":[53],"possibility":[55],"of":[56,73,89],"label":[57],"switching,":[58],"and":[59,76],"chain":[60],"summarization":[61],"methodologies":[62],"clustering":[65],"on":[66],"particular":[68],"model,":[69,75],"namely":[70],"mixture":[72],"multinomials":[74],"show":[77],"that":[78],"fairly":[79],"simple":[80],"can":[82],"be":[83],"employed,":[84],"while":[85],"still":[86],"producing":[87],"clusterings":[88],"superior":[90],"quality":[91],"compared":[92],"to":[93],"those":[94],"produced":[95],"with":[96],"EM":[98],"algorithm.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}