{"id":"https://openalex.org/W2061922307","doi":"https://doi.org/10.1145/2623330.2623715","title":"A dirichlet multinomial mixture model-based approach for short text clustering","display_name":"A dirichlet multinomial mixture model-based approach for short text clustering","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2061922307","doi":"https://doi.org/10.1145/2623330.2623715","mag":"2061922307"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th 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":null,"display_name":"Jianhua Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianhua Yin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100630868","display_name":"Jianyong Wang","orcid":"https://orcid.org/0000-0002-7555-170X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyong Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":32.2515,"has_fulltext":false,"cited_by_count":550,"citation_normalized_percentile":{"value":0.9973475,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998000264167786,"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":0.9998000264167786,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9950000047683716,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9850999712944031,"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":0.8217868208885193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481490969657898},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6612917184829712},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.6003745794296265},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.5933182239532471},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5363351702690125},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46417924761772156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37741944193840027},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.33237284421920776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20701473951339722},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16131752729415894},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08476999402046204}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8217868208885193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481490969657898},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6612917184829712},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.6003745794296265},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.5933182239532471},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5363351702690125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46417924761772156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37741944193840027},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.33237284421920776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20701473951339722},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16131752729415894},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08476999402046204},{"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":1,"locations":[{"id":"doi:10.1145/2623330.2623715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W1501500081","https://openalex.org/W1506806321","https://openalex.org/W1532325895","https://openalex.org/W1550206324","https://openalex.org/W1663973292","https://openalex.org/W1767233158","https://openalex.org/W1880262756","https://openalex.org/W1981276685","https://openalex.org/W1989753615","https://openalex.org/W1992402718","https://openalex.org/W2011430131","https://openalex.org/W2015623780","https://openalex.org/W2025653016","https://openalex.org/W2028544407","https://openalex.org/W2088314245","https://openalex.org/W2097089247","https://openalex.org/W2097417931","https://openalex.org/W2107743791","https://openalex.org/W2110591510","https://openalex.org/W2135631383","https://openalex.org/W2138615112","https://openalex.org/W2140336868","https://openalex.org/W2142838865","https://openalex.org/W2158866759","https://openalex.org/W2162833336","https://openalex.org/W2165232124","https://openalex.org/W2165612380","https://openalex.org/W2165874743","https://openalex.org/W2252275596","https://openalex.org/W2267760512","https://openalex.org/W2478540127","https://openalex.org/W4233135949","https://openalex.org/W4235169531","https://openalex.org/W4302572840"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W2497860580","https://openalex.org/W2352674739","https://openalex.org/W2891616219","https://openalex.org/W3204672119"],"abstract_inverted_index":{"Short":[0],"text":[1,51],"clustering":[2,52,78,122],"has":[3],"become":[4],"an":[5],"increasingly":[6],"important":[7],"task":[8],"with":[9,67,89],"the":[10,44,62,72,77,90,101],"popularity":[11],"of":[12,64,76,95,104],"social":[13],"media":[14],"like":[15],"Twitter,":[16],"Google+,":[17],"and":[18,30,74,80,92,98],"Facebook.":[19],"It":[20],"is":[21,81],"a":[22,38,68],"challenging":[23],"problem":[24,94],"due":[25],"to":[26,54,83],"its":[27],"sparse,":[28],"high-dimensional,":[29],"large-volume":[31],"characteristics.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"proposed":[37],"collapsed":[39],"Gibbs":[40],"Sampling":[41],"algorithm":[42],"for":[43,49],"Dirichlet":[45],"Multinomial":[46],"Mixture":[47],"model":[48],"short":[50,96],"(abbr.":[53],"GSDMM).":[55],"We":[56],"found":[57],"that":[58,112],"GSDMM":[59,85,113],"can":[60,86,99,114],"infer":[61],"number":[63],"clusters":[65],"automatically":[66],"good":[69],"balance":[70],"between":[71],"completeness":[73],"homogeneity":[75],"results,":[79],"fast":[82],"converge.":[84],"also":[87],"cope":[88],"sparse":[91],"high-dimensional":[93],"texts,":[97],"obtain":[100],"representative":[102],"words":[103],"each":[105],"cluster.":[106],"Our":[107],"extensive":[108],"experimental":[109],"study":[110],"shows":[111],"achieve":[115],"significantly":[116],"better":[117],"performance":[118],"than":[119],"three":[120],"other":[121],"models.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":68},{"year":2022,"cited_by_count":67},{"year":2021,"cited_by_count":82},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":58},{"year":2018,"cited_by_count":47},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":16}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}