{"id":"https://openalex.org/W1979297777","doi":"https://doi.org/10.1109/nlpke.2008.4906817","title":"A novel feature weight algorithm for text categorization","display_name":"A novel feature weight algorithm for text categorization","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W1979297777","doi":"https://doi.org/10.1109/nlpke.2008.4906817","mag":"1979297777"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2008.4906817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014243831","display_name":"Wenqian Shang","orcid":"https://orcid.org/0009-0005-0146-1524"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqian Shang","raw_affiliation_strings":["School of Computer, Communication University of China, China","School of Computer, Communication University of China, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Communication University of China, China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"School of Computer, Communication University of China, Beijing","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102058856","display_name":"Hongbin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I1308199089","display_name":"Harbin University","ror":"https://ror.org/00ey9xa07","country_code":"CN","type":"education","lineage":["https://openalex.org/I1308199089"]},{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Dong","raw_affiliation_strings":["National Science Park of Harbin Engineering University, Harbin, China","Nat. Sci. Park of Harbin Eng. Univ., Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Science Park of Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I1308199089","https://openalex.org/I151727225"]},{"raw_affiliation_string":"Nat. Sci. Park of Harbin Eng. Univ., Harbin","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020477193","display_name":"Haibin Zhu","orcid":"https://orcid.org/0000-0003-1922-1631"},"institutions":[{"id":"https://openalex.org/I138900291","display_name":"Nipissing University","ror":"https://ror.org/05k14ba46","country_code":"CA","type":"education","lineage":["https://openalex.org/I138900291"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haibin Zhu","raw_affiliation_strings":["Department of Computer Science, Nipissing University, North Bay, ONT, Canada","Dept. of Comput. Sci., Nipissing Univ., North Bay, ON"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nipissing University, North Bay, ONT, Canada","institution_ids":["https://openalex.org/I138900291"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Nipissing Univ., North Bay, ON","institution_ids":["https://openalex.org/I138900291"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760898","display_name":"Yongbin Wang","orcid":"https://orcid.org/0000-0002-1370-8150"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Wang","raw_affiliation_strings":["School of Computer, Communication University of China, China","School of Computer, Communication University of China, Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Communication University of China, China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"School of Computer, Communication University of China, Beijing","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9926000237464905,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9878000020980835,"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/bottleneck","display_name":"Bottleneck","score":0.7998363971710205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681647539138794},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7473428249359131},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7444647550582886},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7265430688858032},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7054775953292847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6513210535049438},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6004453301429749},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5762746334075928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5648859739303589},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.46452343463897705},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4613492786884308},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45701438188552856},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3879140317440033},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.371841162443161},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3601718544960022},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09228169918060303}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7998363971710205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681647539138794},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7473428249359131},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7444647550582886},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7265430688858032},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7054775953292847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6513210535049438},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6004453301429749},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5762746334075928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648859739303589},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.46452343463897705},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4613492786884308},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45701438188552856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3879140317440033},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.371841162443161},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3601718544960022},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09228169918060303},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/nlpke.2008.4906817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Natural Language Processing and Knowledge Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W35497897","https://openalex.org/W202303397","https://openalex.org/W1549887922","https://openalex.org/W1550206324","https://openalex.org/W1577943466","https://openalex.org/W1594031697","https://openalex.org/W1924689489","https://openalex.org/W1950462534","https://openalex.org/W1983078185","https://openalex.org/W1986913017","https://openalex.org/W1993934121","https://openalex.org/W2005422315","https://openalex.org/W2076287442","https://openalex.org/W2096152098","https://openalex.org/W2105948726","https://openalex.org/W2114535528","https://openalex.org/W2122111042","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2161140950","https://openalex.org/W2170806743","https://openalex.org/W2330820318","https://openalex.org/W2370156863","https://openalex.org/W2435251607","https://openalex.org/W3085162807","https://openalex.org/W4241865841","https://openalex.org/W6608351394","https://openalex.org/W6632852417","https://openalex.org/W6632865047","https://openalex.org/W6634666188","https://openalex.org/W6640670853","https://openalex.org/W6646300278","https://openalex.org/W6682304300","https://openalex.org/W6717827561","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"With":[0],"the":[1,4,13,47,65,78,103,111],"development":[2],"of":[3,8,25,49,60,69,81,113],"Web,":[5],"large":[6],"numbers":[7],"documents":[9],"are":[10,27],"put":[11],"onto":[12],"Internet.":[14],"More":[15],"and":[16,22,34,67,74],"more":[17,33,35],"digital":[18],"libraries,":[19],"news":[20],"sources":[21],"inner":[23],"data":[24],"companies":[26],"available.":[28],"Automatic":[29],"text":[30,43,50,61,82],"categorization":[31,51,104],"becomes":[32],"important":[36],"for":[37],"dealing":[38],"with":[39],"massive":[40],"data.":[41],"However,":[42],"preprocessing":[44,62],"is":[45],"still":[46],"bottleneck":[48],"based":[52],"on":[53,90],"vector":[54],"space":[55],"model":[56],"(VSM).":[57],"The":[58,107],"result":[59],"directly":[63],"affects":[64],"performance":[66,105],"precision":[68],"categorization.":[70],"Moreover,":[71],"feature":[72,75,91,97],"selection":[73],"weight":[76,98],"become":[77],"major":[79],"obstacles":[80],"preprocessing.":[83],"In":[84],"this":[85,114],"paper,":[86],"we":[87],"mainly":[88],"focus":[89],"weight.":[92],"We":[93],"present":[94],"a":[95],"novel":[96],"algorithm----TF-Gini":[99],"that":[100],"can":[101],"improve":[102],"significantly.":[106],"experiment":[108],"results":[109],"verify":[110],"effectiveness":[112],"algorithm.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
