{"id":"https://openalex.org/W2096349503","doi":"https://doi.org/10.1109/icdm.2003.1251013","title":"A feature selection framework for text filtering","display_name":"A feature selection framework for text filtering","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2096349503","doi":"https://doi.org/10.1109/icdm.2003.1251013","mag":"2096349503"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1251013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1251013","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/A5050012027","display_name":"Zhaohui Zheng","orcid":"https://orcid.org/0000-0002-7303-4856"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Z. Zheng","raw_affiliation_strings":["CEDAR, Department of Computer Science and Engineering, State University of New York, USA","CEDAR, State Univ. of New York, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"CEDAR, Department of Computer Science and Engineering, State University of New York, USA","institution_ids":["https://openalex.org/I1327163397"]},{"raw_affiliation_string":"CEDAR, State Univ. of New York, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063869451","display_name":"Rohini K. Srihari","orcid":"https://orcid.org/0000-0001-7454-6872"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]},{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohini Srihari","raw_affiliation_strings":["CEDAR, Department of Computer Science and Engineering, State University of New York, USA","CEDAR, State Univ. of New York, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"CEDAR, Department of Computer Science and Engineering, State University of New York, USA","institution_ids":["https://openalex.org/I1327163397"]},{"raw_affiliation_string":"CEDAR, State Univ. of New York, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102711181","display_name":"Sargur N. Srihari","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]},{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sargur Srihari","raw_affiliation_strings":["CEDAR, Department of Computer Science and Engineering, State University of New York, USA","CEDAR, State Univ. of New York, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"CEDAR, Department of Computer Science and Engineering, State University of New York, USA","institution_ids":["https://openalex.org/I1327163397"]},{"raw_affiliation_string":"CEDAR, State Univ. of New York, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050012027"],"corresponding_institution_ids":["https://openalex.org/I1327163397","https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":1.3491,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.84843031,"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":"705","last_page":"708"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9911999702453613,"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/T10057","display_name":"Face and Expression Recognition","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7848418951034546},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6889811754226685},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6592400074005127},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6125629544258118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6095111966133118},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5658400058746338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49052590131759644},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48933809995651245},{"id":"https://openalex.org/keywords/square","display_name":"Square (algebra)","score":0.46934354305267334},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.4413931667804718},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29690128564834595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21893590688705444}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7848418951034546},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6889811754226685},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6592400074005127},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6125629544258118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6095111966133118},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5658400058746338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49052590131759644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48933809995651245},{"id":"https://openalex.org/C135692309","wikidata":"https://www.wikidata.org/wiki/Q111124","display_name":"Square (algebra)","level":2,"score":0.46934354305267334},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.4413931667804718},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29690128564834595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21893590688705444},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdm.2003.1251013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1251013","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1523389133","https://openalex.org/W1983078185","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2138229177","https://openalex.org/W2435251607","https://openalex.org/W4392042140","https://openalex.org/W6680524308","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W3102623159","https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2366911843","https://openalex.org/W2350577681","https://openalex.org/W2322239237","https://openalex.org/W3147584709","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,15,25,70],"new":[3,71],"framework":[4,55],"for":[5],"local":[6],"feature":[7,16,53,61,95,125],"selection":[8,54,62,96,126],"in":[9],"text":[10,129],"filtering.":[11],"In":[12],"this":[13],"framework,":[14],"set":[17,26,37],"is":[18],"constructed":[19],"per":[20],"category":[21],"by":[22],"first":[23],"selecting":[24],"of":[27,31,38,42,69,109],"terms":[28,39],"highly":[29,40],"indicative":[30,41],"membership":[32],"(positive":[33],"set)":[34],"and":[35,46,78,88,105,112,116],"another":[36],"nonmembership":[43],"(negative":[44],"set),":[45],"then":[47],"combining":[48],"these":[49],"two":[50,106],"sets.":[51,80],"This":[52],"not":[56],"only":[57],"unifies":[58],"several":[59],"standard":[60,89],"methods,":[63],"but":[64],"also":[65],"facilitates":[66],"the":[67,76,85,123],"proposal":[68],"method":[72,87,127],"that":[73,122],"optimally":[74],"combines":[75],"positive":[77],"negative":[79],"The":[81,119],"experimental":[82],"comparison":[83],"between":[84],"proposed":[86,107,124],"methods":[90],"was":[91],"conducted":[92],"on":[93],"six":[94],"metrics:":[97],"chi-square,":[98],"correlation":[99],"coefficient,":[100],"odds":[101,110],"ratio,":[102],"GSS":[103,113],"coefficient":[104],"variants":[108],"ratio":[111],"coefficient:":[114],"OR-square":[115],"GSS-square":[117],"respectively.":[118],"results":[120],"show":[121],"improves":[128],"filtering":[130],"performance.":[131]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}