{"id":"https://openalex.org/W2163167172","doi":"https://doi.org/10.1177/0165551512470054","title":"Probability-based text clustering algorithm by alternately repeating two operations","display_name":"Probability-based text clustering algorithm by alternately repeating two operations","publication_year":2013,"publication_date":"2013-01-29","ids":{"openalex":"https://openalex.org/W2163167172","doi":"https://doi.org/10.1177/0165551512470054","mag":"2163167172"},"language":"en","primary_location":{"id":"doi:10.1177/0165551512470054","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551512470054","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-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/A5100347769","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-1846-6445"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881571","display_name":"Yuanchao Liu","orcid":"https://orcid.org/0009-0007-0430-7658"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchao Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004324294","display_name":"Bingquan Liu","orcid":"https://orcid.org/0000-0001-6352-2170"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingquan Liu","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048326379","display_name":"Lei Lin","orcid":"https://orcid.org/0000-0002-1161-8565"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Lin","raw_affiliation_strings":["MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE-MS Key Laboratory of Natural Language Processing and Speech, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.9471,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89022403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"39","issue":"3","first_page":"372","last_page":"383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9988999962806702,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9988999962806702,"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/T11106","display_name":"Data Management and Algorithms","score":0.9959999918937683,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9947999715805054,"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":0.8244123458862305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7641552686691284},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6474099159240723},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5309777855873108},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.477113276720047},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45817869901657104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45588454604148865},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39386555552482605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37023138999938965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3282065987586975},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15580624341964722},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12662643194198608},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08997416496276855}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8244123458862305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641552686691284},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6474099159240723},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5309777855873108},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.477113276720047},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45817869901657104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45588454604148865},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39386555552482605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37023138999938965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3282065987586975},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15580624341964722},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12662643194198608},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08997416496276855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551512470054","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551512470054","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1679913846","https://openalex.org/W1790954942","https://openalex.org/W1975930544","https://openalex.org/W1990072650","https://openalex.org/W1994781462","https://openalex.org/W2009452011","https://openalex.org/W2014615172","https://openalex.org/W2018197961","https://openalex.org/W2034662733","https://openalex.org/W2040683545","https://openalex.org/W2045498778","https://openalex.org/W2049607461","https://openalex.org/W2051344535","https://openalex.org/W2057351803","https://openalex.org/W2060371459","https://openalex.org/W2068487168","https://openalex.org/W2072643409","https://openalex.org/W2073841815","https://openalex.org/W2094710333","https://openalex.org/W2096810317","https://openalex.org/W2107303832","https://openalex.org/W2109144580","https://openalex.org/W2113072182","https://openalex.org/W2113161543","https://openalex.org/W2122473047","https://openalex.org/W2124369546","https://openalex.org/W2125070513","https://openalex.org/W2137763598","https://openalex.org/W2146483359","https://openalex.org/W2153233077","https://openalex.org/W2162161511","https://openalex.org/W2168701898","https://openalex.org/W2425246132","https://openalex.org/W4243461609","https://openalex.org/W4247444580","https://openalex.org/W4249591146","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W1795405792","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"Owing":[0],"to":[1,10,12,61,81],"the":[2,20,74,129],"rapid":[3],"advance":[4],"of":[5,16,27,119],"internet":[6,46],"technology,":[7],"users":[8],"have":[9],"face":[11],"a":[13,37,93],"large":[14],"amount":[15],"raw":[17],"data":[18],"from":[19],"World":[21],"Wide":[22],"Web":[23],"every":[24],"day,":[25],"most":[26],"which":[28],"is":[29,50,58,108,132,137],"displayed":[30],"in":[31,110],"text":[32,42,85,91,97,126,148],"format.":[33],"This":[34,113],"situation":[35],"brings":[36],"great":[38],"demand":[39],"for":[40],"efficient":[41],"analysis":[43],"techniques":[44],"by":[45,100],"users.":[47],"Since":[48],"clustering":[49,75,98,149],"unsupervised":[51],"and":[52,124],"requires":[53],"no":[54],"prior":[55],"knowledge,":[56],"it":[57],"extensively":[59],"adopted":[60],"help":[62],"analyse":[63],"textual":[64],"data.":[65],"Unfortunately,":[66],"as":[67,69,106],"far":[68,79],"I":[70],"know,":[71],"almost":[72],"all":[73],"algorithms":[76],"proposed":[77,109],"so":[78],"fail":[80],"deal":[82],"with":[83,145],"large-scale":[84,90],"collection.":[86],"For":[87],"precisely":[88],"classifying":[89],"collection,":[92],"novel":[94],"probability":[95],"based":[96],"algorithm":[99,114],"alternately":[101],"repeating":[102],"two":[103,117],"operations":[104,118],"(abbreviated":[105],"PTCART)":[107],"this":[111],"paper.":[112],"just":[115],"repeats":[116],"(a)":[120],"feature":[121],"set":[122],"construction":[123],"(b)":[125],"partition":[127,131],"until":[128],"optimal":[130],"reached.":[133],"Its":[134],"convergent":[135],"capacity":[136],"also":[138],"validated.":[139],"Experiments":[140],"results":[141],"demonstrate":[142],"that,":[143],"compared":[144],"several":[146],"popular":[147],"algorithms,":[150],"PTCART":[151],"has":[152],"excellent":[153],"performance.":[154]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
