{"id":"https://openalex.org/W1999928587","doi":"https://doi.org/10.1145/2396761.2398457","title":"Feature selection based on term frequency and T-test for text categorization","display_name":"Feature selection based on term frequency and T-test for text categorization","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W1999928587","doi":"https://doi.org/10.1145/2396761.2398457","mag":"1999928587"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100612161","display_name":"Deqing Wang","orcid":"https://orcid.org/0000-0001-6441-4390"},"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":"Deqing Wang","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, BeiJing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637526","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-2501-712X"},"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":"Hui Zhang","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, BeiJing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448618","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-1973-6168"},"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":"Rui Liu","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, BeiJing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109299440","display_name":"Weifeng Lv","orcid":"https://orcid.org/0000-0002-7061-9509"},"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":"Weifeng Lv","raw_affiliation_strings":["Beihang University, Beijing, China","BeiHang University, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"BeiHang University, BeiJing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.0813,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87801526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1482","last_page":"1486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9937000274658203,"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":0.9882000088691711,"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/term","display_name":"Term (time)","score":0.7815585136413574},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7228188514709473},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6578965187072754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6550703644752502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5921759009361267},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5675488114356995},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5512307286262512},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5311654210090637},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5123249292373657},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.46614471077919006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4660312831401825},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4508492648601532},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4334961473941803},{"id":"https://openalex.org/keywords/frequency","display_name":"Frequency","score":0.4176332950592041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.350762277841568},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33866727352142334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33091723918914795},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24520468711853027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.230411559343338}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7815585136413574},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7228188514709473},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6578965187072754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6550703644752502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921759009361267},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5675488114356995},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5512307286262512},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5311654210090637},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5123249292373657},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.46614471077919006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4660312831401825},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4508492648601532},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4334961473941803},{"id":"https://openalex.org/C199075045","wikidata":"https://www.wikidata.org/wiki/Q762856","display_name":"Frequency","level":2,"score":0.4176332950592041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.350762277841568},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33866727352142334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33091723918914795},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24520468711853027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.230411559343338},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2396761.2398457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"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/W1549887922","https://openalex.org/W1550206324","https://openalex.org/W1620204465","https://openalex.org/W1972640883","https://openalex.org/W1978394996","https://openalex.org/W2019191301","https://openalex.org/W2068833644","https://openalex.org/W2074466695","https://openalex.org/W2099975513","https://openalex.org/W2103333826","https://openalex.org/W2113579719","https://openalex.org/W2116780029","https://openalex.org/W2118020653","https://openalex.org/W2119821739","https://openalex.org/W2138550913","https://openalex.org/W2153635508","https://openalex.org/W2165728620","https://openalex.org/W2166317455","https://openalex.org/W2435251607","https://openalex.org/W2998216295","https://openalex.org/W2998237634","https://openalex.org/W3005526988","https://openalex.org/W3120421331","https://openalex.org/W4205110562","https://openalex.org/W4285719527","https://openalex.org/W4298443330"],"related_works":["https://openalex.org/W2372663604","https://openalex.org/W2111353337","https://openalex.org/W2371357422","https://openalex.org/W1482708182","https://openalex.org/W2328484534","https://openalex.org/W1973637371","https://openalex.org/W2367691850","https://openalex.org/W3023878085","https://openalex.org/W2391234281","https://openalex.org/W2372424341"],"abstract_inverted_index":{"Much":[0],"work":[1],"has":[2],"been":[3],"done":[4],"on":[5,12,73,82,91,117],"feature":[6,78,139],"selection.":[7],"Existing":[8],"methods":[9,24,141],"are":[10,32,65],"based":[11,81,90],"document":[13,52],"frequency,":[14,84],"such":[15],"as":[16,68],"Chi-Square":[17],"Statistic,":[18],"Information":[19],"Gain":[20],"etc.":[21],"However,":[22],"these":[23],"have":[25],"two":[26,118],"shortcomings:":[27],"one":[28,47],"is":[29,41,94,129],"that":[30,42,125],"they":[31,43],"not":[33],"reliable":[34],"for":[35],"low-frequency":[36],"terms,":[37],"and":[38,53,85,110,144,150],"the":[39,55,77,98,101,107,111,137],"other":[40],"only":[44],"count":[45],"whether":[46],"term":[48,56,83,105],"occurs":[49],"in":[50,146],"a":[51,62,87,104],"ignore":[54],"frequency.":[57],"Actually,":[58],"high-frequency":[59],"terms":[60,147],"within":[61],"specific":[63,108],"category":[64,109],"often":[66],"regards":[67],"discriminators.":[69],"This":[70],"paper":[71],"focuses":[72],"how":[74],"to":[75,96,131],"construct":[76],"selection":[79,140],"function":[80],"proposes":[86],"new":[88,127],"approach":[89,128],"t-test,":[92],"which":[93],"used":[95],"measure":[97],"diversity":[99],"of":[100,103,148],"distributions":[102],"between":[106],"entire":[112],"corpus.":[113],"Extensive":[114],"comparative":[115],"experiments":[116],"text":[119],"corpora":[120],"using":[121],"three":[122],"classifiers":[123],"show":[124],"our":[126],"comparable":[130],"or":[132,133],"slightly":[134],"better":[135],"than":[136],"state-of-the-art":[138],"(i.e.,":[142],"chi2,":[143],"IG)":[145],"macro-F1":[149],"micro-F1":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}