{"id":"https://openalex.org/W2087242439","doi":"https://doi.org/10.1145/2542050.2542079","title":"Document clustering using dirichlet process mixture model of von Mises-Fisher distributions","display_name":"Document clustering using dirichlet process mixture model of von Mises-Fisher distributions","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2087242439","doi":"https://doi.org/10.1145/2542050.2542079","mag":"2087242439"},"language":"en","primary_location":{"id":"doi:10.1145/2542050.2542079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2542050.2542079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Symposium on Information and Communication Technology - SoICT '13","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/A5113584950","display_name":"Nguy\u1ec5n Kim Anh","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Nguyen Kim Anh","raw_affiliation_strings":["Hanoi University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096011394","display_name":"Nguyen The Tam","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen The Tam","raw_affiliation_strings":["Hanoi University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022485068","display_name":"Linh Ngo Van","orcid":"https://orcid.org/0000-0002-0011-5137"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngo Van Linh","raw_affiliation_strings":["Hanoi University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113584950"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":2.4046,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90283385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9815000295639038,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6245216131210327},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6024636626243591},{"id":"https://openalex.org/keywords/von-mises-yield-criterion","display_name":"von Mises yield criterion","score":0.5971190929412842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5522089004516602},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4310358762741089},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3569149672985077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3419302701950073},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.20858588814735413},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09743386507034302},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.06852993369102478},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06400328874588013}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6245216131210327},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6024636626243591},{"id":"https://openalex.org/C155165730","wikidata":"https://www.wikidata.org/wiki/Q1319519","display_name":"von Mises yield criterion","level":3,"score":0.5971190929412842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5522089004516602},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4310358762741089},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3569149672985077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3419302701950073},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.20858588814735413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09743386507034302},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.06852993369102478},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06400328874588013},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2542050.2542079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2542050.2542079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Symposium on Information and Communication Technology - SoICT '13","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":17,"referenced_works":["https://openalex.org/W1967687583","https://openalex.org/W1981081578","https://openalex.org/W1985512973","https://openalex.org/W2025653016","https://openalex.org/W2047555270","https://openalex.org/W2069429561","https://openalex.org/W2070232376","https://openalex.org/W2072169887","https://openalex.org/W2080094394","https://openalex.org/W2080838288","https://openalex.org/W2080972498","https://openalex.org/W2097417931","https://openalex.org/W2126802698","https://openalex.org/W2127498532","https://openalex.org/W2145001205","https://openalex.org/W2151967501","https://openalex.org/W2165874743"],"related_works":["https://openalex.org/W1505113900","https://openalex.org/W3199802165","https://openalex.org/W172625365","https://openalex.org/W2123614589","https://openalex.org/W194234896","https://openalex.org/W2368760070","https://openalex.org/W3042958706","https://openalex.org/W4297791708","https://openalex.org/W2087242439","https://openalex.org/W2002937977"],"abstract_inverted_index":{"Document":[0],"clustering":[1,32,70,85,128],"has":[2],"become":[3],"an":[4],"increasingly":[5],"important":[6],"technique":[7],"for":[8,45,60],"unsupervised":[9],"document":[10],"organization,":[11],"automatic":[12],"topic":[13],"extraction,":[14],"and":[15,116],"fast":[16],"information":[17],"retrieval":[18],"or":[19],"filtering.":[20],"This":[21],"paper":[22],"proposes":[23],"a":[24,55,100],"Dirichlet":[25],"process":[26,86],"mixture":[27],"(DPM)":[28],"model":[29,63],"approach":[30,98,123],"to":[31,69,94],"directional":[33],"data":[34,46],"based":[35],"on":[36,48,99],"the":[37,49,61,76,84,96,125],"von":[38],"Mises-Fisher":[39],"(vMF)":[40],"distribution,":[41],"which":[42],"arises":[43],"naturally":[44],"distributed":[47],"unit":[50],"hypersphere.":[51],"We":[52,90],"have":[53],"developed":[54],"mean-field":[56],"variational":[57],"inference":[58],"algorithm":[59],"DPM":[62],"of":[64,78,103],"vMFs":[65],"that":[66,121],"is":[67,80],"applied":[68],"text":[71,106],"documents.":[72],"Using":[73],"this":[74],"model,":[75],"number":[77,102],"clusters":[79],"determined":[81],"automatically":[82],"after":[83],"rather":[87],"than":[88],"pre-estimated.":[89],"conducted":[91],"extensive":[92],"experiments":[93],"evaluate":[95],"proposed":[97],"large":[101],"high":[104],"dimensional":[105],"datasets.":[107],"Empirical":[108],"experimental":[109],"results":[110],"over":[111],"NMI":[112],"(Normalized":[113],"Mutual":[114],"Information)":[115],"Purity":[117],"evaluation":[118],"measures":[119],"demonstrate":[120],"our":[122],"outperforms":[124],"four":[126],"state-of-the-art":[127],"algorithms.":[129]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}