{"id":"https://openalex.org/W2117423052","doi":"https://doi.org/10.1109/icdm.2002.1183881","title":"Text document categorization by term association","display_name":"Text document categorization by term association","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2117423052","doi":"https://doi.org/10.1109/icdm.2002.1183881","mag":"2117423052"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183881","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/A5077692930","display_name":"Maria-Luiza Antonie","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"M.-L. Antonie","raw_affiliation_strings":["University of Alberta, Canada","Alberta Univ., Edmonton, Alta., Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Alberta Univ., Edmonton, Alta., Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053745515","display_name":"Osmar R. Za\u0131\u0308ane","orcid":"https://orcid.org/0000-0002-0060-5988"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"O.R. Zaiane","raw_affiliation_strings":["University of Alberta, Canada","Alberta Univ., Edmonton, Alta., Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Alberta Univ., Edmonton, Alta., Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077692930"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":45.6225,"has_fulltext":false,"cited_by_count":224,"citation_normalized_percentile":{"value":0.99758088,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.996399998664856,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.8043583631515503},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7487443685531616},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7198371887207031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256378293037415},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5856295824050903},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.5401034355163574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45825186371803284},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41410893201828003},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37990307807922363},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33110857009887695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3284839987754822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043583631515503},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7487443685531616},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7198371887207031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256378293037415},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5856295824050903},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.5401034355163574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45825186371803284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41410893201828003},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37990307807922363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33110857009887695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3284839987754822}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdm.2002.1183881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183881","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.4365","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.4365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~zaiane/postscript/icdm02-1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1528447234","https://openalex.org/W1924689489","https://openalex.org/W1969572066","https://openalex.org/W2005422315","https://openalex.org/W2027875450","https://openalex.org/W2044854172","https://openalex.org/W2049384587","https://openalex.org/W2060683726","https://openalex.org/W2062847911","https://openalex.org/W2064853889","https://openalex.org/W2094934653","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2126850915","https://openalex.org/W2135276756","https://openalex.org/W2140617045","https://openalex.org/W2149684865","https://openalex.org/W2154642793","https://openalex.org/W2166559705","https://openalex.org/W2167681385","https://openalex.org/W4239149380","https://openalex.org/W4252403066","https://openalex.org/W6631572448","https://openalex.org/W6678971004","https://openalex.org/W6680723932","https://openalex.org/W6682837551","https://openalex.org/W6684495928"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2106892947"],"abstract_inverted_index":{"A":[0],"good":[1,54],"text":[2,13,65,109,155,158],"classifier":[3,6,42,175],"is":[4,43],"a":[5,16,53,104,140,154],"that":[7,26,30,111,173],"efficiently":[8],"categorizes":[9],"large":[10],"sets":[11],"of":[12,40],"documents":[14],"in":[15,49,122,139],"reasonable":[17],"time":[18],"frame":[19],"and":[20,25,61,80,145,147,165,167,188],"with":[21],"an":[22],"acceptable":[23],"accuracy,":[24],"provides":[27],"classification":[28,85,184],"rules":[29,138,151,191],"are":[31,75,185,192],"human":[32,193],"readable":[33],"for":[34,56,63,107],"possible":[35],"fine-tuning.":[36],"If":[37],"the":[38,41,57,94,123,134,150,174,189],"training":[39,180],"also":[44],"quick,":[45],"this":[46,100],"could":[47],"become":[48],"some":[50,74,81],"application":[51],"domains":[52],"asset":[55],"classifier.":[58,156],"Many":[59],"techniques":[60,117],"algorithms":[62],"automatic":[64,108],"categorization":[66,110,159],"have":[67],"been":[68],"devised.":[69],"According":[70],"to":[71,152,162],"published":[72],"literature,":[73],"more":[76,83],"accurate":[77],"than":[78,87],"others,":[79],"provide":[82],"interpretable":[84],"models":[86],"others.":[88],"However,":[89],"none":[90],"can":[91],"combine":[92],"all":[93],"beneficial":[95],"properties":[96],"enumerated":[97],"above.":[98],"In":[99,178],"paper":[101],"we":[102],"present":[103],"novel":[105],"approach":[106],"borrows":[112],"from":[113],"market":[114],"basket":[115],"analysis":[116],"using":[118,149],"association":[119,137],"rule":[120],"mining":[121],"data-mining":[124],"field.":[125],"We":[126],"focus":[127],"on":[128,169],"two":[129],"major":[130],"problems:":[131],"(1)":[132],"finding":[133],"best":[135],"term":[136],"textual":[141],"database":[142],"by":[143],"generating":[144],"pruning;":[146],"(2)":[148],"build":[153],"Our":[157],"method":[160],"proves":[161],"be":[163],"efficient":[164],"effective,":[166],"experiments":[168],"well-known":[170],"collections":[171],"show":[172],"performs":[176],"well.":[177],"addition,":[179],"as":[181,183],"well":[182],"both":[186],"fast":[187],"generated":[190],"readable.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}