{"id":"https://openalex.org/W4246266734","doi":"https://doi.org/10.1109/tsmcb.2012.2212430","title":"SAIL: Summation-bAsed Incremental Learning for Information-Theoretic Text Clustering","display_name":"SAIL: Summation-bAsed Incremental Learning for Information-Theoretic Text Clustering","publication_year":2012,"publication_date":"2012-09-10","ids":{"openalex":"https://openalex.org/W4246266734","doi":"https://doi.org/10.1109/tsmcb.2012.2212430"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcb.2012.2212430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2212430","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","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/A5060815634","display_name":"Jie Cao","orcid":"https://orcid.org/0000-0002-9942-3243"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Cao","raw_affiliation_strings":["Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063565261","display_name":"Zhiang Wu","orcid":"https://orcid.org/0000-0002-0591-1861"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiang Wu","raw_affiliation_strings":["Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Provincial Key Laboratory of E-Business, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112210049","display_name":"Junjie Wu","orcid":"https://orcid.org/0009-0009-4993-8976"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Wu","raw_affiliation_strings":["Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations, the School of Economics and Management, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations, the School of Economics and Management, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101862104","display_name":"Hui Xiong","orcid":"https://orcid.org/0000-0001-6016-6465"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":["Management Science and Information Systems Department, Rutgers University, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Management Science and Information Systems Department, Rutgers University, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6542,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.96010636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"43","issue":"2","first_page":"570","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9969000220298767,"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/T10057","display_name":"Face and Expression Recognition","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8331479430198669},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"k-means clustering","score":0.7762726545333862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6547179222106934},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.6146522164344788},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5008985996246338},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48236221075057983},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46603864431381226},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27721381187438965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2644103169441223}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8331479430198669},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.7762726545333862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6547179222106934},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.6146522164344788},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5008985996246338},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48236221075057983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46603864431381226},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27721381187438965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2644103169441223},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmcb.2012.2212430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2012.2212430","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1554524169","https://openalex.org/W1595613095","https://openalex.org/W1651093245","https://openalex.org/W1965555277","https://openalex.org/W1965667542","https://openalex.org/W1981081578","https://openalex.org/W1984907405","https://openalex.org/W1997661122","https://openalex.org/W2010334716","https://openalex.org/W2025653016","https://openalex.org/W2032108856","https://openalex.org/W2069657950","https://openalex.org/W2087962968","https://openalex.org/W2096765209","https://openalex.org/W2097872774","https://openalex.org/W2105053450","https://openalex.org/W2111310758","https://openalex.org/W2112737239","https://openalex.org/W2127042504","https://openalex.org/W2127218421","https://openalex.org/W2129630294","https://openalex.org/W2145001205","https://openalex.org/W2147936330","https://openalex.org/W2149148023","https://openalex.org/W2166168249","https://openalex.org/W2170403573","https://openalex.org/W2319660501","https://openalex.org/W2478708596","https://openalex.org/W2482589566","https://openalex.org/W2497532187","https://openalex.org/W4205885661","https://openalex.org/W4255387915","https://openalex.org/W6635548358","https://openalex.org/W6637231022","https://openalex.org/W6674201379","https://openalex.org/W6675866969","https://openalex.org/W6678914141","https://openalex.org/W6682124274"],"related_works":["https://openalex.org/W2952821581","https://openalex.org/W4311618633","https://openalex.org/W2053086704","https://openalex.org/W2185776155","https://openalex.org/W4379648054","https://openalex.org/W2604976738","https://openalex.org/W2592235592","https://openalex.org/W2904779692","https://openalex.org/W2120258591","https://openalex.org/W3049268462"],"abstract_inverted_index":{"Information-theoretic":[0],"clustering":[1,9,24,143,185,201],"aims":[2],"to":[3,44,71,82],"exploit":[4],"information-theoretic":[5],"measures":[6],"as":[7,27,51,181],"the":[8,18,28,59,85,117,122,131,136,142,148,155,184,200],"criteria.":[10],"A":[11],"common":[12],"practice":[13],"on":[14,34,171],"this":[15,92,95],"topic":[16],"is":[17,43,56,159],"so-called":[19],"Info-Kmeans,":[20],"which":[21,69,158],"performs":[22],"K-means":[23],"with":[25,46,179],"KL-divergence":[26,73,120],"proximity":[29],"function.":[30],"While":[31],"expert":[32],"efforts":[33],"Info-Kmeans":[35,106,188],"have":[36,176],"shown":[37,177],"promising":[38],"results,":[39],"a":[40,77,99,163,182,204],"remaining":[41],"challenge":[42],"deal":[45],"high-dimensional":[47,66],"sparse":[48],"data":[49],"such":[50],"text":[52,67,174],"corpora.":[53],"Indeed,":[54],"it":[55],"possible":[57],"that":[58],"centroids":[60,83],"contain":[61],"many":[62],"zero-value":[63],"features":[64],"for":[65,105],"vectors,":[68],"leads":[70],"infinite":[72],"values":[74],"and":[75,153,195],"creates":[76],"dilemma":[78,133],"in":[79,94,166],"assigning":[80],"objects":[81],"during":[84],"iteration":[86],"process":[87],"of":[88,119,125,138,187,207],"Info-Kmeans.":[89],"To":[90,140],"meet":[91],"challenge,":[93],"paper,":[96],"we":[97,145],"propose":[98,154],"Summation-bAsed":[100],"Incremental":[101],"Learning":[102],"(SAIL)":[103],"algorithm":[104],"clustering.":[107],"Specifically,":[108],"by":[109,121,135,162],"using":[110],"an":[111],"equivalent":[112],"objective":[113],"function,":[114],"SAIL":[115,180],"replaces":[116],"computation":[118,124],"incremental":[123],"Shannon":[126],"entropy.":[127],"This":[128],"can":[129,189],"avoid":[130],"zero-feature":[132],"caused":[134],"use":[137],"KL-divergence.":[139],"improve":[141,199],"quality,":[144],"further":[146],"introduce":[147],"variable":[149],"neighborhood":[150],"search":[151],"scheme":[152,165],"V-SAIL":[156,194],"algorithm,":[157],"then":[160],"accelerated":[161],"multithreaded":[164],"PV-SAIL.":[167],"Our":[168],"experimental":[169],"results":[170],"various":[172],"real-world":[173],"collections":[175],"that,":[178],"booster,":[183],"performance":[186],"be":[190],"significantly":[191],"improved.":[192],"Also,":[193],"PV-SAIL":[196],"indeed":[197],"help":[198],"quality":[202],"at":[203],"lower":[205],"cost":[206],"computation.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
