{"id":"https://openalex.org/W2158913012","doi":"https://doi.org/10.1109/nlpke.2008.4906808","title":"Divergence-based feature selection for naïve Bayes text classification","display_name":"Divergence-based feature selection for naïve Bayes text classification","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2158913012","doi":"https://doi.org/10.1109/nlpke.2008.4906808","mag":"2158913012"},"language":"en","primary_location":{"id":"doi:10.1109/nlpke.2008.4906808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906808","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/A5101961245","display_name":"Huizhen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizhen Wang","raw_affiliation_strings":["Natural Language Processing Laboratory, Northeastern University, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natural Language Processing Laboratory, Northeastern University, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370145","display_name":"Jingbo Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Natural Language Processing Laboratory, Northeastern University, Liaoning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natural Language Processing Laboratory, Northeastern University, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070399630","display_name":"Keh\u2010Yih Su","orcid":"https://orcid.org/0000-0003-2838-1362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keh-Yih Su","raw_affiliation_strings":["Behavior Design Corporation, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Behavior Design Corporation, Hsinchu, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21924866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9998999834060669,"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":0.9927999973297119,"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":0.9923999905586243,"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/divergence","display_name":"Divergence (linguistics)","score":0.8418455719947815},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7061306238174438},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6799011826515198},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.669960618019104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6627823710441589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6379427909851074},{"id":"https://openalex.org/keywords/bayes-error-rate","display_name":"Bayes error rate","score":0.5916135907173157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5603407621383667},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5435992479324341},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5211755633354187},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5152573585510254},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5067988038063049},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46423426270484924},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3012317419052124},{"id":"https://openalex.org/keywords/bayes-classifier","display_name":"Bayes classifier","score":0.1924419403076172},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10596457123756409}],"concepts":[{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.8418455719947815},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7061306238174438},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6799011826515198},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.669960618019104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6627823710441589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6379427909851074},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.5916135907173157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5603407621383667},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5435992479324341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5211755633354187},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5152573585510254},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5067988038063049},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46423426270484924},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3012317419052124},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.1924419403076172},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10596457123756409},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nlpke.2008.4906808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nlpke.2008.4906808","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":[{"score":0.6100000143051147,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"},{"id":"https://openalex.org/F4320334924","display_name":"Program for New Century Excellent Talents in University","ror":"https://ror.org/01mv9t934"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W1550206324","https://openalex.org/W1587362683","https://openalex.org/W1623080549","https://openalex.org/W1833785989","https://openalex.org/W2017337590","https://openalex.org/W2040241219","https://openalex.org/W2052332599","https://openalex.org/W2060216474","https://openalex.org/W2096152098","https://openalex.org/W2099111195","https://openalex.org/W2105330923","https://openalex.org/W2112520519","https://openalex.org/W2121537574","https://openalex.org/W2125591439","https://openalex.org/W2134873765","https://openalex.org/W2136075087","https://openalex.org/W2138104808","https://openalex.org/W2148633389","https://openalex.org/W2149684865","https://openalex.org/W2149706766","https://openalex.org/W2356966757","https://openalex.org/W2435251607","https://openalex.org/W4236137412","https://openalex.org/W6608351394","https://openalex.org/W6632865047","https://openalex.org/W6679703030","https://openalex.org/W6680087038"],"related_works":["https://openalex.org/W2374047926","https://openalex.org/W179179905","https://openalex.org/W2394466068","https://openalex.org/W2360982908","https://openalex.org/W2086147528","https://openalex.org/W2393473353","https://openalex.org/W1973600295","https://openalex.org/W145653800","https://openalex.org/W4312309445","https://openalex.org/W2537862391"],"abstract_inverted_index":{"A":[0],"new":[1],"divergence-based":[2],"approach":[3,63],"to":[4],"feature":[5,25],"selection":[6],"for":[7,29,68],"naive":[8],"Bayes":[9],"text":[10],"classification":[11],"is":[12,26,39],"proposed":[13,62],"in":[14],"this":[15,18],"paper.":[16],"In":[17],"approach,":[19],"the":[20,42,61],"discrimination":[21,66],"power":[22,67],"of":[23],"each":[24],"directly":[27],"used":[28],"ranking":[30],"various":[31,47],"features":[32],"through":[33],"a":[34],"criterion":[35],"named":[36],"overall-divergence,":[37],"which":[38],"based":[40],"on":[41,78],"divergence":[43],"measures":[44],"evaluated":[45],"between":[46],"class":[48],"density":[49],"function":[50],"pairs.":[51],"Compared":[52],"with":[53],"other":[54],"state-of-the-art":[55],"algorithms":[56],"(e.g.":[57],"IG":[58],"and":[59,72],"CHI),":[60],"shows":[64],"more":[65],"classifying":[69],"confusing":[70],"classes,":[71],"achieves":[73],"better":[74],"or":[75],"comparable":[76],"performance":[77],"evaluation":[79],"data":[80],"sets.":[81]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}