{"id":"https://openalex.org/W2798640246","doi":"https://doi.org/10.1631/fitee.1601761","title":"A new feature selection method for handling redundant information in text classification","display_name":"A new feature selection method for handling redundant information in text classification","publication_year":2018,"publication_date":"2018-02-01","ids":{"openalex":"https://openalex.org/W2798640246","doi":"https://doi.org/10.1631/fitee.1601761","mag":"2798640246"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1601761","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601761","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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/A5100707542","display_name":"Youwei Wang","orcid":"https://orcid.org/0000-0002-3925-3422"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"You-wei Wang","raw_affiliation_strings":["School of Information, Central University of Finance and Economics, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"School of Information, Central University of Finance and Economics, Beijing, 100081, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101813002","display_name":"Lizhou Feng","orcid":"https://orcid.org/0000-0002-1010-8539"},"institutions":[{"id":"https://openalex.org/I193524592","display_name":"Tianjin University of Finance and Economics","ror":"https://ror.org/05ev1jb90","country_code":"CN","type":"education","lineage":["https://openalex.org/I193524592"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-zhou Feng","raw_affiliation_strings":["School of Science and Engineering, Tianjin University of Finance and Economics, Tianjin, 300222, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Engineering, Tianjin University of Finance and Economics, Tianjin, 300222, China","institution_ids":["https://openalex.org/I193524592"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100707542"],"corresponding_institution_ids":["https://openalex.org/I137867983"],"apc_list":null,"apc_paid":null,"fwci":1.1402,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83308025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"2","first_page":"221","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9864000082015991,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9854000210762024,"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/feature-selection","display_name":"Feature selection","score":0.8020306825637817},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.7283226251602173},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7175993919372559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012051939964294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6250993013381958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5806910991668701},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5402491092681885},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5360024571418762},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5351776480674744},{"id":"https://openalex.org/keywords/minimum-redundancy-feature-selection","display_name":"Minimum redundancy feature selection","score":0.5154155492782593},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.513899564743042},{"id":"https://openalex.org/keywords/information-gain-ratio","display_name":"Information gain ratio","score":0.5093063116073608},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4566033184528351},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4464692771434784},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.4375547468662262},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42359262704849243},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18191584944725037}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.8020306825637817},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.7283226251602173},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7175993919372559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012051939964294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6250993013381958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806910991668701},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5402491092681885},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5360024571418762},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5351776480674744},{"id":"https://openalex.org/C16811321","wikidata":"https://www.wikidata.org/wiki/Q17138905","display_name":"Minimum redundancy feature selection","level":3,"score":0.5154155492782593},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.513899564743042},{"id":"https://openalex.org/C202185110","wikidata":"https://www.wikidata.org/wiki/Q6031086","display_name":"Information gain ratio","level":3,"score":0.5093063116073608},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4566033184528351},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4464692771434784},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.4375547468662262},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42359262704849243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18191584944725037},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1601761","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601761","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W636917482","https://openalex.org/W637422688","https://openalex.org/W1550206324","https://openalex.org/W1553682320","https://openalex.org/W1594031697","https://openalex.org/W1891087341","https://openalex.org/W1982589161","https://openalex.org/W1993885071","https://openalex.org/W1999635750","https://openalex.org/W1999928587","https://openalex.org/W2013301630","https://openalex.org/W2025500887","https://openalex.org/W2044289181","https://openalex.org/W2063016658","https://openalex.org/W2068833644","https://openalex.org/W2069321575","https://openalex.org/W2071712180","https://openalex.org/W2073491590","https://openalex.org/W2075961691","https://openalex.org/W2089923329","https://openalex.org/W2090552208","https://openalex.org/W2098162425","https://openalex.org/W2102831150","https://openalex.org/W2118020653","https://openalex.org/W2149236946","https://openalex.org/W2149684865","https://openalex.org/W2149772057","https://openalex.org/W2150874198","https://openalex.org/W2153635508","https://openalex.org/W2154053567","https://openalex.org/W2156483112","https://openalex.org/W2158140178","https://openalex.org/W2160390935","https://openalex.org/W2162223169","https://openalex.org/W2169384781","https://openalex.org/W2292011317","https://openalex.org/W2301416341","https://openalex.org/W2307589391","https://openalex.org/W2435251607","https://openalex.org/W4246354968","https://openalex.org/W4252684946","https://openalex.org/W6630226126","https://openalex.org/W6674809819"],"related_works":["https://openalex.org/W3164528651","https://openalex.org/W2985680200","https://openalex.org/W2042378471","https://openalex.org/W2058380590","https://openalex.org/W2352513827","https://openalex.org/W1566319786","https://openalex.org/W2069321575","https://openalex.org/W2371481268","https://openalex.org/W577421504","https://openalex.org/W2533731304"],"abstract_inverted_index":{"Feature":[0],"selection":[1,37,70,186],"is":[2,73,141],"an":[3,67],"important":[4],"approach":[5],"to":[6,47,75,82],"dimensionality":[7],"reduction":[8],"in":[9,19,90,105,121,208,212],"the":[10,17,21,24,43,49,54,84,87,100,106,134,138,162,166,202,205],"field":[11],"of":[12,16,56,137,146,204],"text":[13,213],"classification.":[14,214],"Because":[15],"difficulty":[18],"handling":[20,209],"problem":[22],"that":[23,133,145],"selected":[25],"features":[26,89,102],"always":[27],"contain":[28],"redundant":[29,44,88,210],"information,":[30],"we":[31],"propose":[32],"a":[33,77,96],"new":[34],"simple":[35],"feature":[36,69,78,159,181,185],"method,":[38],"which":[39],"can":[40],"effectively":[41],"filter":[42],"features.":[45],"First,":[46],"calculate":[48],"relationship":[50],"between":[51],"two":[52],"words,":[53],"definitions":[55],"word":[57],"frequency":[58],"based":[59,187],"relevance":[60],"and":[61,99,118,125,155,161,177,183,191],"correlative":[62],"redundancy":[63],"are":[64,92,103,110,128],"introduced.":[65],"Furthermore,":[66],"optimal":[68],"(OFS)":[71],"method":[72,140,168,207],"chosen":[74],"obtain":[76],"subset":[79],"FS1.":[80],"Finally,":[81],"improve":[83],"execution":[85],"speed,":[86],"FS1":[91],"filtered":[93,101],"by":[94],"combining":[95],"predetermined":[97],"threshold,":[98],"memorized":[104],"linked":[107],"lists.":[108],"Experiments":[109],"carried":[111],"out":[112],"on":[113,188],"three":[114],"datasets":[115],"(WebKB,":[116],"20-Newsgroups,":[117],"Reuters-21578)":[119],"where":[120],"support":[122],"vector":[123],"machines":[124],"na\u00efve":[126],"Bayes":[127],"used.":[129],"The":[130],"results":[131,200],"show":[132],"classification":[135,197],"accuracy":[136],"proposed":[139,167,206],"generally":[142],"higher":[143],"than":[144,171],"typical":[147,172],"traditional":[148],"methods":[149,175],"(information":[150],"gain,":[151],"improved":[152,156],"Gini":[153],"index,":[154],"comprehensively":[157],"measured":[158],"selection)":[160],"OFS":[163],"methods.":[164],"Moreover,":[165],"runs":[169],"faster":[170],"mutual":[173,179],"information-based":[174,180],"(improved":[176],"normalized":[178],"selections,":[182],"multilabel":[184],"maximum":[189],"dependency":[190],"minimum":[192],"redundancy)":[193],"while":[194],"simultaneously":[195],"ensuring":[196],"accuracy.":[198],"Statistical":[199],"validate":[201],"effectiveness":[203],"information":[211]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}