{"id":"https://openalex.org/W2152886525","doi":"https://doi.org/10.1109/icdm.2003.1250951","title":"CBC: clustering based text classification requiring minimal labeled data","display_name":"CBC: clustering based text classification requiring minimal labeled data","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W2152886525","doi":"https://doi.org/10.1109/icdm.2003.1250951","mag":"2152886525"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on 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/A5016928764","display_name":"Hua-Jun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hua-Jun Zeng","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111967949","display_name":"Xuan-Hui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan-Hui Wang","raw_affiliation_strings":["University of Science and Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665770","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0001-5252-4752"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551313","display_name":"Hongjun L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongjun Lu","raw_affiliation_strings":["Department of Computer Science, HKUST, Kowloon, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, HKUST, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016928764"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":6.9319,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.96779949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","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/T12535","display_name":"Machine Learning and Data Classification","score":0.9962000250816345,"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/T12072","display_name":"Machine Learning and Algorithms","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/labeled-data","display_name":"Labeled data","score":0.8110008835792542},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7472306489944458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062110304832458},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.689516544342041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6801597476005554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5972349047660828},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5147857666015625},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4484710991382599},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4290265738964081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32448309659957886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32247889041900635}],"concepts":[{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.8110008835792542},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7472306489944458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062110304832458},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.689516544342041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6801597476005554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5972349047660828},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5147857666015625},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4484710991382599},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4290265738964081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32448309659957886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32247889041900635},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2003.1250951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.7917","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.7917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/%7Ezhengc/papers/ICDM.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1574877594","https://openalex.org/W1596382552","https://openalex.org/W1924689489","https://openalex.org/W1983078185","https://openalex.org/W1986913017","https://openalex.org/W1993934121","https://openalex.org/W2005422315","https://openalex.org/W2011948397","https://openalex.org/W2037603696","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2071106922","https://openalex.org/W2094934653","https://openalex.org/W2097089247","https://openalex.org/W2107008379","https://openalex.org/W2134089414","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2163614729","https://openalex.org/W3171280080","https://openalex.org/W6640261747","https://openalex.org/W6659845429","https://openalex.org/W6676132248","https://openalex.org/W6679849079","https://openalex.org/W6682304300","https://openalex.org/W6796760531"],"related_works":["https://openalex.org/W3172695526","https://openalex.org/W1757117718","https://openalex.org/W2889166412","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3104108945","https://openalex.org/W2033364610"],"abstract_inverted_index":{"Semisupervised":[0],"learning":[1],"methods":[2,30],"construct":[3],"classifiers":[4,91],"using":[5],"both":[6,61],"labeled":[7,35,63,75,84,99,123],"and":[8,40,64],"unlabeled":[9,14,65,79],"training":[10,58],"data":[11,15,36,45,80],"samples.":[12],"While":[13],"samples":[16,81],"can":[17,92],"help":[18],"to":[19,26],"improve":[20],"the":[21,43,62,71,74,87,97,104,120],"accuracy":[22],"of":[23,73,78,103,122],"trained":[24,95],"models":[25],"certain":[27],"extent,":[28],"existing":[29,117],"still":[31],"face":[32],"difficulties":[33],"when":[34,119],"is":[37,67,107,125],"not":[38],"sufficient":[39],"biased":[41],"against":[42],"underlying":[44],"distribution.":[46],"We":[47],"present":[48],"a":[49],"clustering":[50],"based":[51,85],"classification":[52],"(CBC)":[53],"approach.":[54],"Using":[55],"this":[56],"approach,":[57],"data,":[59,66],"including":[60],"first":[68],"clustered":[69],"with":[70,96],"guidance":[72],"data.":[76],"Some":[77],"are":[82],"then":[83],"on":[86],"clusters":[88],"obtained.":[89],"Discriminative":[90],"subsequently":[93],"be":[94],"expanded":[98],"dataset.":[100],"The":[101],"effectiveness":[102],"proposed":[105],"method":[106],"justified":[108],"analytically.":[109],"Our":[110],"experimental":[111],"results":[112],"demonstrated":[113],"that":[114],"CBC":[115],"outperforms":[116],"algorithms":[118],"size":[121],"dataset":[124],"very":[126],"small.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}