{"id":"https://openalex.org/W2340455672","doi":"https://doi.org/10.1109/ialp.2015.7451549","title":"Weighted Document Frequency for feature selection in text classification","display_name":"Weighted Document Frequency for feature selection in text classification","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2340455672","doi":"https://doi.org/10.1109/ialp.2015.7451549","mag":"2340455672"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2015.7451549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2015.7451549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Asian Language Processing (IALP)","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/A5103324036","display_name":"Baoli Li","orcid":"https://orcid.org/0009-0009-4797-1318"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoli Li","raw_affiliation_strings":["College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100925632","display_name":"Qiuling Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuling Yan","raw_affiliation_strings":["College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100983613","display_name":"Zhenqiang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenqiang Xu","raw_affiliation_strings":["College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031376449","display_name":"Guicai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guicai Wang","raw_affiliation_strings":["College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Henan University of Technology, Zhengzhou, CHINA","institution_ids":["https://openalex.org/I36152291"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36152291"],"apc_list":null,"apc_paid":null,"fwci":0.8731,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84018479,"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":"132","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9861000180244446,"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":0.9828000068664551,"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","display_name":"Feature (linguistics)","score":0.6929803490638733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6883096694946289},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6538633108139038},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5972424745559692},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5876260995864868},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5448373556137085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5393787026405334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5180683135986328},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5071308612823486},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5041118860244751},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48999014496803284},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4593939781188965},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4497232735157013},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34460538625717163},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32903411984443665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28545814752578735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15479937195777893},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.09873732924461365},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05978947877883911}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6929803490638733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883096694946289},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6538633108139038},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5972424745559692},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5876260995864868},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5448373556137085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393787026405334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5180683135986328},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5071308612823486},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5041118860244751},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48999014496803284},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4593939781188965},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4497232735157013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34460538625717163},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32903411984443665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28545814752578735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15479937195777893},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.09873732924461365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05978947877883911},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2015.7451549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2015.7451549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Asian Language Processing (IALP)","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":20,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1550206324","https://openalex.org/W1574901103","https://openalex.org/W1964042173","https://openalex.org/W2103333826","https://openalex.org/W2118020653","https://openalex.org/W2118585731","https://openalex.org/W2153635508","https://openalex.org/W2167101736","https://openalex.org/W2435251607","https://openalex.org/W2911681169","https://openalex.org/W2998216295","https://openalex.org/W4285719527","https://openalex.org/W6632865047","https://openalex.org/W6634260664","https://openalex.org/W6675969814","https://openalex.org/W6677656871","https://openalex.org/W6717827561","https://openalex.org/W6758972637","https://openalex.org/W7066667914"],"related_works":["https://openalex.org/W2372663604","https://openalex.org/W2611282738","https://openalex.org/W1561627904","https://openalex.org/W3006526473","https://openalex.org/W1573371033","https://openalex.org/W2585523118","https://openalex.org/W4232107035","https://openalex.org/W2080168170","https://openalex.org/W1981887710","https://openalex.org/W83893648"],"abstract_inverted_index":{"In":[0],"the":[1,93,136,139],"past":[2],"research,":[3],"Document":[4],"Frequency":[5],"(DF)":[6],"has":[7],"been":[8],"validated":[9],"to":[10,107,121,125],"be":[11,40,69],"a":[12,33,36,41,43,45,48,56,60,64,81,85,112],"simple":[13],"yet":[14],"quite":[15],"effective":[16],"measure":[17],"for":[18],"feature":[19,61,82,94],"selection":[20],"in":[21,32,63,84,96],"text":[22,132],"classification.":[23],"The":[24,52],"calculation":[25],"is":[26,95,104,117],"based":[27],"on":[28,130],"how":[29,91],"many":[30],"documents":[31],"collection":[34],"contain":[35],"feature,":[37],"which":[38],"can":[39],"word,":[42],"phrase,":[44],"n-gram,":[46],"or":[47],"specially":[49],"derived":[50],"attribute.":[51],"counting":[53],"process":[54],"takes":[55],"binary":[57],"strategy:":[58],"if":[59],"appears":[62,83],"document,":[65,86],"its":[66],"DF":[67,75],"will":[68],"increased":[70],"by":[71],"one.":[72],"This":[73],"traditional":[74],"metric":[76],"concerns":[77],"only":[78],"about":[79],"whether":[80],"but":[87],"does":[88],"not":[89],"consider":[90],"important":[92],"that":[97],"document.":[98],"Obviously,":[99],"thus":[100],"counted":[101],"document":[102,114],"frequency":[103,115],"very":[105],"likely":[106],"introduce":[108],"much":[109],"noise.":[110],"Therefore,":[111],"weighted":[113],"(WDF)":[116],"proposed":[118,140],"and":[119],"expected":[120],"reduce":[122],"such":[123],"noise":[124],"some":[126],"extent.":[127],"Extensive":[128],"experiments":[129],"two":[131],"classification":[133],"datasets":[134],"demonstrate":[135],"effectiveness":[137],"of":[138],"measure.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}