{"id":"https://openalex.org/W2118965172","doi":"https://doi.org/10.1145/1281192.1281220","title":"Feature selection methods for text classification","display_name":"Feature selection methods for text classification","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W2118965172","doi":"https://doi.org/10.1145/1281192.1281220","mag":"2118965172"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and 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/A5061449196","display_name":"Anirban Dasgupta","orcid":"https://orcid.org/0000-0002-8494-3692"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":true,"raw_author_name":"Anirban Dasgupta","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081378199","display_name":"Petros Drineas","orcid":"https://orcid.org/0000-0003-1994-8670"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petros Drineas","raw_affiliation_strings":["RPI"],"affiliations":[{"raw_affiliation_string":"RPI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112448435","display_name":"Boulos Harb","orcid":null},"institutions":[{"id":"https://openalex.org/I2802460994","display_name":"William Penn University","ror":"https://ror.org/03m7qwy32","country_code":"US","type":"education","lineage":["https://openalex.org/I2802460994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boulos Harb","raw_affiliation_strings":["U Penn"],"affiliations":[{"raw_affiliation_string":"U Penn","institution_ids":["https://openalex.org/I2802460994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033006662","display_name":"Michael W. Mahoney","orcid":"https://orcid.org/0000-0001-7920-4652"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Michael W. Mahoney","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061449196"],"corresponding_institution_ids":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":10.7949,"has_fulltext":false,"cited_by_count":164,"citation_normalized_percentile":{"value":0.98238946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"239"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9958999752998352,"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/feature-selection","display_name":"Feature selection","score":0.8686555624008179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993973851203918},{"id":"https://openalex.org/keywords/minimum-redundancy-feature-selection","display_name":"Minimum redundancy feature selection","score":0.6506595611572266},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6456851959228516},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6402029991149902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5886774063110352},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5866576433181763},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5341963171958923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4631459414958954},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.456339031457901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4170839190483093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1649397909641266}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.8686555624008179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993973851203918},{"id":"https://openalex.org/C16811321","wikidata":"https://www.wikidata.org/wiki/Q17138905","display_name":"Minimum redundancy feature selection","level":3,"score":0.6506595611572266},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6456851959228516},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6402029991149902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886774063110352},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5866576433181763},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5341963171958923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4631459414958954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.456339031457901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4170839190483093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1649397909641266},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1281192.1281220","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W27344939","https://openalex.org/W83404773","https://openalex.org/W196871588","https://openalex.org/W658559791","https://openalex.org/W1493036841","https://openalex.org/W1493526108","https://openalex.org/W1494019289","https://openalex.org/W1524688041","https://openalex.org/W1540155273","https://openalex.org/W1549887922","https://openalex.org/W1564518192","https://openalex.org/W1596717185","https://openalex.org/W1813460488","https://openalex.org/W1970974276","https://openalex.org/W1972056194","https://openalex.org/W1993644118","https://openalex.org/W1998058722","https://openalex.org/W2003670573","https://openalex.org/W2005422315","https://openalex.org/W2017337590","https://openalex.org/W2020115667","https://openalex.org/W2037495825","https://openalex.org/W2037679392","https://openalex.org/W2040884411","https://openalex.org/W2043804332","https://openalex.org/W2050559027","https://openalex.org/W2069231281","https://openalex.org/W2103333826","https://openalex.org/W2110652811","https://openalex.org/W2113043986","https://openalex.org/W2114220113","https://openalex.org/W2118020653","https://openalex.org/W2148603752","https://openalex.org/W2149551942","https://openalex.org/W2149684865","https://openalex.org/W2149846618","https://openalex.org/W2150102617","https://openalex.org/W2159416808","https://openalex.org/W2435251607","https://openalex.org/W2535756153","https://openalex.org/W2913668833","https://openalex.org/W2950989697","https://openalex.org/W2951016966","https://openalex.org/W2998216295","https://openalex.org/W3005198936","https://openalex.org/W3005526988","https://openalex.org/W3139361274","https://openalex.org/W4240986158","https://openalex.org/W4285719527","https://openalex.org/W6621858757","https://openalex.org/W6814457508","https://openalex.org/W7024761944","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W74056413","https://openalex.org/W2286904880","https://openalex.org/W2392236103","https://openalex.org/W2954668464","https://openalex.org/W4293525103","https://openalex.org/W41136918","https://openalex.org/W2374344280","https://openalex.org/W2385233088","https://openalex.org/W2384303144","https://openalex.org/W2894871804"],"abstract_inverted_index":{"We":[0,87],"consider":[1],"feature":[2,17,60,79,109,134,148],"selection":[3,18,61,80,110,135],"for":[4,20],"text":[5],"classification":[6,34,41],"both":[7],"theoretically":[8],"and":[9,76,93,104],"empirically.":[10],"Our":[11,116],"main":[12],"result":[13],"is":[14,57],"an":[15],"unsupervised":[16],"strategy":[19,81,122],"which":[21],"we":[22],"give":[23],"worst-case":[24],"theoretical":[25],"guarantees":[26,126],"on":[27,142],"the":[28,32,40,48,51,58,68,90,100,121],"generalization":[29],"power":[30],"of":[31,53,102],"resultant":[33],"function":[35,42],"f":[36,43],"with":[37,63,123,131],"respect":[38],"to":[39,71,74,97],"obtained":[44],"when":[45,75],"keeping":[46],"all":[47],"features.":[49],"To":[50],"best":[52],"our":[54],"knowledge,":[55],"this":[56,78,103],"first":[59],"method":[62],"such":[64],"guarantees.":[65],"In":[66,137],"addition,":[67,138],"analysis":[69],"leads":[70],"insights":[72],"as":[73],"why":[77],"will":[82],"perform":[83],"well":[84,128],"in":[85,129],"practice.":[86],"then":[88],"use":[89],"TechTC-100,":[91],"20-Newsgroups,":[92],"Reuters-RCV2":[94],"data":[95],"sets":[96],"evaluate":[98],"empirically":[99],"performance":[101,125],"two":[105,113],"simpler":[106],"but":[107],"related":[108],"strategies":[111],"against":[112],"commonly-used":[114,133],"strategies.":[115,136],"empirical":[117],"evaluation":[118],"shows":[119],"that":[120],"provable":[124],"performs":[127,140],"comparison":[130],"other":[132],"it":[139],"better":[141],"certain":[143],"datasets":[144],"under":[145],"very":[146],"aggressive":[147],"selection.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":17}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}