{"id":"https://openalex.org/W1995708644","doi":"https://doi.org/10.1145/1081870.1081888","title":"Local sparsity control for naive Bayes with extreme misclassification costs","display_name":"Local sparsity control for naive Bayes with extreme misclassification costs","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W1995708644","doi":"https://doi.org/10.1145/1081870.1081888","mag":"1995708644"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081888","doi":"https://doi.org/10.1145/1081870.1081888","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081888","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"volume":null,"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/A5111761879","display_name":"Aleksander Ko\u0142cz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aleksander Kolcz","raw_affiliation_strings":["AOL, Inc., Dulles, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AOL, Inc., Dulles, VA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5111761879"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7137,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.69514066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"137"},"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":9.999999747378752e-05,"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/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/naive-bayes","display_name":"naive Bayes","score":0.8040000200271606},{"id":"https://openalex.org/keywords/misclassification-cost","display_name":"misclassification cost","score":0.6299999952316284},{"id":"https://openalex.org/keywords/multinomial-naive-bayes","display_name":"multinomial naive Bayes","score":0.8989999890327454},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.8960000276565552},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.8180000185966492},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.5040000081062317},{"id":"https://openalex.org/keywords/classifier-calibration","display_name":"classifier calibration","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.8520187139511108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472796440124512},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6716116666793823},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6022011637687683},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5844773054122925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.562125563621521},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48058080673217773},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.47737738490104675},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.47358518838882446},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4560118317604065},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4167248010635376},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3626023828983307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32553184032440186},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10842058062553406},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1081870.1081888","doi":"https://doi.org/10.1145/1081870.1081888","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081888","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W167016754","https://openalex.org/W1485321296","https://openalex.org/W1549656520","https://openalex.org/W1549887922","https://openalex.org/W1550206324","https://openalex.org/W1574901103","https://openalex.org/W1579410832","https://openalex.org/W1598033630","https://openalex.org/W1618905105","https://openalex.org/W1646807883","https://openalex.org/W1817561967","https://openalex.org/W1924689489","https://openalex.org/W2012942264","https://openalex.org/W2017337590","https://openalex.org/W2018077356","https://openalex.org/W2060216474","https://openalex.org/W2067432306","https://openalex.org/W2084848593","https://openalex.org/W2089086886","https://openalex.org/W2092114106","https://openalex.org/W2094934653","https://openalex.org/W2096581064","https://openalex.org/W2096942889","https://openalex.org/W2098824882","https://openalex.org/W2103333826","https://openalex.org/W2133002765","https://openalex.org/W2140336868","https://openalex.org/W2140390894","https://openalex.org/W2140785063","https://openalex.org/W2141253686","https://openalex.org/W2155653793","https://openalex.org/W2435251607","https://openalex.org/W2440833291","https://openalex.org/W2913668833","https://openalex.org/W2914453346","https://openalex.org/W3005526988","https://openalex.org/W3141271909"],"related_works":["https://openalex.org/W1562823344","https://openalex.org/W2946138657","https://openalex.org/W3210203749","https://openalex.org/W2537862391","https://openalex.org/W4376149419","https://openalex.org/W3177713506","https://openalex.org/W1549887922","https://openalex.org/W1558666744","https://openalex.org/W2469540655","https://openalex.org/W2927655512"],"abstract_inverted_index":{"In":[0,118,140,155],"applications":[1,47],"of":[2,13,22,125,135,151,173],"data":[3],"mining":[4,46],"characterized":[5],"by":[6],"highly":[7,136],"skewed":[8],"misclassification":[9,138],"costs":[10],"certain":[11],"types":[12],"errors":[14],"become":[15],"virtually":[16],"unacceptable.":[17],"This":[18],"limits":[19],"the":[20,110,123,133,156,174,180],"utility":[21],"a":[23,26],"classifier":[24],"to":[25,40,49,61,76,98,169,179],"range":[27],"in":[28,44,101,132,195],"which":[29,37],"such":[30],"constraints":[31],"can":[32,52,96],"be":[33,41,53,62,193],"met.":[34],"Naive":[35,79,130,161,181],"Bayes,":[36],"has":[38,83],"proven":[39],"very":[42],"useful":[43],"text":[45],"due":[48],"high":[50,71],"scalability,":[51],"particularly":[54],"affected.":[55],"Although":[56],"its":[57,64,87],"0/1":[58],"loss":[59],"tends":[60],"small,":[63],"misclassifications":[65],"are":[66,185],"often":[67],"made":[68],"with":[69,142,163],"apparently":[70],"confidence.":[72],"Aside":[73],"from":[74],"efforts":[75],"better":[77],"calibrate":[78],"Bayes":[80,131,162,182],"scores,":[81],"it":[82],"been":[84],"shown":[85],"that":[86,188],"accuracy":[88],"depends":[89],"on":[90],"document":[91,115,145],"sparsity":[92,105,127,165],"and":[93,109],"feature":[94,153,190],"selection":[95,191],"lead":[97],"marked":[99],"improvement":[100],"classification":[102],"performance.":[103],"Traditionally,":[104],"is":[106,167],"controlled":[107],"globally,":[108],"result":[111],"for":[112,129],"any":[113],"particular":[114],"may":[116,192],"vary.":[117],"this":[119],"work":[120],"we":[121,147],"examine":[122],"merits":[124],"local":[126,164,189],"control":[128,166],"context":[134],"asymmetric":[137],"costs.":[139],"experiments":[141],"three":[143],"benchmark":[144],"collections":[146],"demonstrate":[148],"clear":[149],"advantages":[150],"document-level":[152],"selection.":[154],"extreme":[157],"cost":[158,197],"setting,":[159],"multinomial":[160],"able":[168],"outperform":[170],"even":[171],"some":[172],"recently":[175],"proposed":[176],"effective":[177],"improvements":[178],"classifier.":[183],"There":[184],"also":[186],"indications":[187],"preferable":[194],"different":[196],"settings.":[198]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}