{"id":"https://openalex.org/W2050559027","doi":"https://doi.org/10.1145/1015330.1015388","title":"Text categorization with many redundant features","display_name":"Text categorization with many redundant features","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2050559027","doi":"https://doi.org/10.1145/1015330.1015388","mag":"2050559027"},"language":"en","primary_location":{"id":"doi:10.1145/1015330.1015388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","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/A5013932834","display_name":"Evgeniy Gabrilovich","orcid":"https://orcid.org/0000-0001-7933-1926"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Evgeniy Gabrilovich","raw_affiliation_strings":["Israel Institute of Technology, Haifa (Israel)"],"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology, Haifa (Israel)","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088024319","display_name":"Shaul Markovitch","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shaul Markovitch","raw_affiliation_strings":["Israel Institute of Technology, Haifa (Israel)"],"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology, Haifa (Israel)","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013932834"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":19.8886,"has_fulltext":false,"cited_by_count":202,"citation_normalized_percentile":{"value":0.99332088,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9945999979972839,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9894000291824341,"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/categorization","display_name":"Categorization","score":0.8868987560272217},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7822116613388062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761737585067749},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7348437309265137},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7097762823104858},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7091776728630066},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6280568242073059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6093064546585083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5291531682014465},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.513769268989563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5021040439605713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4202689230442047},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3910972774028778},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3203456401824951}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8868987560272217},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7822116613388062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761737585067749},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7348437309265137},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7097762823104858},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7091776728630066},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6280568242073059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093064546585083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5291531682014465},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.513769268989563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5021040439605713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4202689230442047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3910972774028778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3203456401824951},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1015330.1015388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1015330.1015388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twenty-first international conference on Machine learning  - ICML '04","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W140312209","https://openalex.org/W1482260847","https://openalex.org/W1493036841","https://openalex.org/W1493526108","https://openalex.org/W1522930027","https://openalex.org/W1576520375","https://openalex.org/W1592212241","https://openalex.org/W1999776614","https://openalex.org/W2005422315","https://openalex.org/W2038721957","https://openalex.org/W2040241219","https://openalex.org/W2103333826","https://openalex.org/W2112511705","https://openalex.org/W2113043986","https://openalex.org/W2118020653","https://openalex.org/W2125055259","https://openalex.org/W2140390894","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2156909104","https://openalex.org/W2166706824","https://openalex.org/W2170602716","https://openalex.org/W2170654002","https://openalex.org/W2188770627","https://openalex.org/W2435251607","https://openalex.org/W3017143921","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2156571267","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2111353337","https://openalex.org/W2371357422"],"abstract_inverted_index":{"Text":[0],"categorization":[1,40,58,97],"algorithms":[2],"usually":[3],"represent":[4],"documents":[5],"as":[6],"bags":[7],"of":[8,18,27,38,56,70,90,116,130,137],"words":[9],"and":[10,34,108],"consequently":[11],"have":[12],"to":[13,111,135,145],"deal":[14],"with":[15,41,63,124],"huge":[16],"numbers":[17],"features.":[19,66],"Most":[20],"previous":[21],"studies":[22],"found":[23],"that":[24,35,60,104,120,136],"the":[25,36,75,128],"majority":[26],"these":[28,71],"features":[29,72,127],"are":[30,61,73],"relevant":[31],"for":[32,121],"classification,":[33],"performance":[37,129],"text":[39,57],"support":[42],"vector":[43],"machines":[44],"peaks":[45],"when":[46],"no":[47],"feature":[48,106,141],"selection":[49,142],"is":[50,132],"performed.":[51],"We":[52,99,118],"describe":[53],"a":[54,84,101,113,149],"class":[55],"problems":[59,122],"characterized":[62],"many":[64],"redundant":[65,126],"Even":[67],"though":[68],"most":[69],"relevant,":[74],"underlying":[76],"concepts":[77],"can":[78],"be":[79],"concisely":[80],"captured":[81],"using":[82],"only":[83],"few":[85],"features,":[86],"while":[87,139],"keeping":[88],"all":[89],"them":[91],"has":[92],"substantially":[93],"detrimental":[94],"effect":[95],"on":[96],"accuracy.":[98],"develop":[100],"novel":[102],"measure":[103],"captures":[105],"redundancy,":[107],"use":[109],"it":[110],"analyze":[112],"large":[114],"collection":[115],"datasets.":[117],"show":[119],"plagued":[123],"numerous":[125],"C4.5":[131,147],"significantly":[133],"superior":[134],"SVM,":[138],"aggressive":[140],"allows":[143],"SVM":[144],"beat":[146],"by":[148],"narrow":[150],"margin.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":19}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}