{"id":"https://openalex.org/W2143517590","doi":"https://doi.org/10.1109/icdm.2002.1183902","title":"Discriminative category matching: efficient text classification for huge document collections","display_name":"Discriminative category matching: efficient text classification for huge document collections","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2143517590","doi":"https://doi.org/10.1109/icdm.2002.1183902","mag":"2143517590"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","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/A5101491411","display_name":"Gabriel Pui Cheong Fung","orcid":"https://orcid.org/0000-0002-7408-795X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"G.P.C. Fung","raw_affiliation_strings":["Department of System Engineering & Engineering Management, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of System Engineering & Engineering Management, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075642293","display_name":"Jeffrey Xu Yu","orcid":"https://orcid.org/0000-0002-9738-827X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"J.X. Yu","raw_affiliation_strings":["Department of System Engineering & Engineering Management, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of System Engineering & Engineering Management, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","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, Hang Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hang Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101491411"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.8277,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87910092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9979000091552734,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/discriminative-model","display_name":"Discriminative model","score":0.8877364993095398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7942221164703369},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6247508525848389},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5895370841026306},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5059730410575867},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4988222122192383},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.4961625039577484},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4893483519554138},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4672546088695526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46467193961143494},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43123680353164673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39371803402900696},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15483710169792175},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.07547622919082642}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8877364993095398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942221164703369},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6247508525848389},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5895370841026306},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5059730410575867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4988222122192383},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.4961625039577484},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4893483519554138},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4672546088695526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46467193961143494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43123680353164673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39371803402900696},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15483710169792175},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.07547622919082642},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2002.1183902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330412","display_name":"Scheme for Promotion of Academic and Research Collaboration","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1550206324","https://openalex.org/W1592322370","https://openalex.org/W1817561967","https://openalex.org/W1924689489","https://openalex.org/W1978394996","https://openalex.org/W1979495886","https://openalex.org/W1997841190","https://openalex.org/W2005422315","https://openalex.org/W2035754578","https://openalex.org/W2037074646","https://openalex.org/W2067970404","https://openalex.org/W2107935041","https://openalex.org/W2108807072","https://openalex.org/W2114535528","https://openalex.org/W2123504579","https://openalex.org/W2126502509","https://openalex.org/W2149684865","https://openalex.org/W2149892594","https://openalex.org/W2156909104","https://openalex.org/W2164641162","https://openalex.org/W2466512847","https://openalex.org/W6632865047","https://openalex.org/W6640261747","https://openalex.org/W6659550781","https://openalex.org/W6682304300","https://openalex.org/W6683984541"],"related_works":["https://openalex.org/W2147276454","https://openalex.org/W2386683790","https://openalex.org/W2105380710","https://openalex.org/W761008918","https://openalex.org/W2154282042","https://openalex.org/W2053389710","https://openalex.org/W2060776304","https://openalex.org/W2889701379","https://openalex.org/W2417411439","https://openalex.org/W2029157577"],"abstract_inverted_index":{"With":[0],"the":[1,9,42,49,61,91,120],"rapid":[2],"growth":[3],"of":[4,90,98,119],"textual":[5],"information":[6],"available":[7],"on":[8],"Internet,":[10],"having":[11],"a":[12,39,53,66,106,129],"good":[13],"model":[14,44,51,78],"for":[15,52,76],"classifying":[16],"and":[17,33,80,82,128],"managing":[18],"documents":[19,26],"automatically":[20],"is":[21,57,142],"undoubtedly":[22],"important.":[23],"When":[24],"more":[25],"are":[27,133],"archived,":[28],"new":[29,31],"terms,":[30],"concepts":[32],"concept-drift":[34],"will":[35],"frequently":[36],"appear":[37],"Without":[38],"doubt,":[40],"updating":[41],"classification":[43,69,93,109],"frequently,":[45],"rather":[46],"than":[47],"using":[48,125],"old":[50],"very":[54],"long":[55],"period":[56],"absolutely":[58],"essential.":[59],"Here,":[60],"challenges":[62],"are:":[63],"a)":[64],"obtain":[65],"high":[67],"accuracy":[68],"model;":[70],"b)":[71],"consume":[72],"low":[73,85],"computational":[74],"time":[75],"both":[77],"training":[79],"operation;":[81],"c)":[83],"occupy":[84],"storage":[86],"space.":[87],"However,":[88],"none":[89],"existing":[92],"approaches":[94],"could":[95,116],"achieve":[96,117],"all":[97,118],"these":[99],"requirements.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"propose":[105],"novel":[107],"text":[108],"approach,":[110],"called":[111],"discriminative":[112],"category":[113],"matching,":[114],"which":[115],"stated":[121],"characteristics.":[122],"Extensive":[123],"experiments":[124],"two":[126],"benchmarks":[127],"large":[130],"real-life":[131],"collection":[132],"conducted.":[134],"The":[135],"encouraging":[136],"results":[137],"indicated":[138],"that":[139],"our":[140],"approach":[141],"highly":[143],"feasible.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}