{"id":"https://openalex.org/W2082461712","doi":"https://doi.org/10.1145/2806416.2806565","title":"Parallel Lazy Semi-Naive Bayes Strategies for Effective and Efficient Document Classification","display_name":"Parallel Lazy Semi-Naive Bayes Strategies for Effective and Efficient Document Classification","publication_year":2015,"publication_date":"2015-10-17","ids":{"openalex":"https://openalex.org/W2082461712","doi":"https://doi.org/10.1145/2806416.2806565","mag":"2082461712"},"language":"en","primary_location":{"id":"doi:10.1145/2806416.2806565","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","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/A5057646226","display_name":"Felipe Viegas","orcid":"https://orcid.org/0000-0001-8121-8607"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Felipe Viegas","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033070469","display_name":"Wellington S. Martins","orcid":"https://orcid.org/0000-0002-9641-2565"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wellington Martins","raw_affiliation_strings":["Universidade Federal de Goi\u00e1s, Goi\u00e2nia, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Goi\u00e1s, Goi\u00e2nia, Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087565388","display_name":"Leonardo Rocha","orcid":"https://orcid.org/0000-0002-4913-4902"},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Rocha","raw_affiliation_strings":["Universidade Federal de S\u00e3o Jo\u00e3o Del Rei, S\u00e2o Jo\u00e2o Del Rei, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de S\u00e3o Jo\u00e3o Del Rei, S\u00e2o Jo\u00e2o Del Rei, Brazil","institution_ids":["https://openalex.org/I166595947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2346,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81299769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1071","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8534187078475952},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7331967353820801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6364016532897949},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.617956280708313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5866724848747253},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5364677906036377},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.43878427147865295},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42335814237594604},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4215611219406128},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17245635390281677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534187078475952},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7331967353820801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6364016532897949},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.617956280708313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866724848747253},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5364677906036377},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.43878427147865295},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42335814237594604},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4215611219406128},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17245635390281677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2806416.2806565","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W66588809","https://openalex.org/W91469012","https://openalex.org/W168332103","https://openalex.org/W961659484","https://openalex.org/W1123003088","https://openalex.org/W1524688041","https://openalex.org/W1532325895","https://openalex.org/W1594013288","https://openalex.org/W1600766826","https://openalex.org/W1817561967","https://openalex.org/W1906182963","https://openalex.org/W1997840447","https://openalex.org/W2011471399","https://openalex.org/W2017309537","https://openalex.org/W2022638422","https://openalex.org/W2043976122","https://openalex.org/W2051158205","https://openalex.org/W2053463056","https://openalex.org/W2081891266","https://openalex.org/W2100522629","https://openalex.org/W2111574971","https://openalex.org/W2111814036","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2118585731","https://openalex.org/W2124724172","https://openalex.org/W2135813353","https://openalex.org/W2140336868","https://openalex.org/W2150102617","https://openalex.org/W2150999626","https://openalex.org/W2217894451","https://openalex.org/W3001645704","https://openalex.org/W4206109200","https://openalex.org/W6639818597","https://openalex.org/W6940864190"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Automatic":[0],"Document":[1],"Classification":[2],"(ADC)":[3],"is":[4,57],"the":[5,83,86,115,127,158,209],"basis":[6],"of":[7,34,62,85,155,157,188,197,208,218],"many":[8],"important":[9,129],"applications":[10],"such":[11,53,66,145,177],"as":[12,54,67,146,178],"spam":[13],"filtering":[14],"and":[15,36,72,151,180,191,202],"content":[16],"organization.":[17],"Naive":[18],"Bayes":[19],"(NB)":[20],"approaches":[21],"are":[22],"a":[23,133,204],"widely":[24],"used":[25],"classification":[26],"paradigm,":[27],"due":[28],"to":[29,47,59,131,143,173,183,220,228],"their":[30],"simplicity,":[31],"efficiency,":[32],"absence":[33],"parameters":[35],"effectiveness.":[37],"However,":[38],"they":[39],"do":[40],"not":[41],"present":[42,203],"competitive":[43],"effectiveness":[44,97,170],"when":[45,141,171,226],"compared":[46,172,227],"other":[48],"modern":[49],"statistical":[50],"learning":[51],"methods,":[52],"SVMs.":[55],"This":[56],"related":[58],"some":[60,138,185],"characteristics":[61],"real":[63],"document":[64],"collections,":[65],"class":[68],"imbalance,":[69],"feature":[70,88],"sparseness":[71],"strong":[73],"relationships":[74],"among":[75],"attributes.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80,194],"investigate":[81],"whether":[82],"relaxation":[84],"NB":[87,116],"independence":[89,117],"assumption":[90],"(aka,":[91],"Semi-NB":[92,107,139,165,190,210],"approaches)":[93],"can":[94,167,223],"improve":[95],"its":[96],"in":[98,236],"large":[99],"text":[100],"collections.":[101],"We":[102,160],"propose":[103],"four":[104],"new":[105],"Lazy":[106,164],"strategies":[108],"that":[109,162,216],"exploit":[110],"different":[111],"ideas":[112],"for":[113],"alleviating":[114],"assumption.":[118],"By":[119],"being":[120],"lazy,":[121],"our":[122,163,232],"solutions":[123],"focus":[124],"only":[125],"on":[126],"most":[128],"features":[130],"classify":[132],"given":[134],"test":[135],"document,":[136],"overcoming":[137],"issues":[140,187],"applied":[142],"ADC":[144,175],"bias":[147],"towards":[148],"larger":[149],"classes":[150],"overfitting":[152],"and/or":[153],"lack":[154],"generalization":[156],"models.":[159],"demonstrate":[161],"proposals":[166,233],"produce":[168],"superior":[169],"state-of-the-art":[174],"classifiers":[176],"SVM":[179],"KNN.":[181],"Moreover,":[182],"overcome":[184],"efficiency":[186],"combining":[189],"lazy":[192],"strategies,":[193],"take":[195],"advantage":[196],"current":[198],"manycore":[199],"GPU":[200],"architectures":[201],"massively":[205],"parallelized":[206],"version":[207],"approaches.":[211],"Our":[212],"experimental":[213],"results":[214],"show":[215],"speedups":[217],"up":[219],"63.36":[221],"times":[222],"be":[224],"obtained":[225],"serial":[229],"solutions,":[230],"making":[231],"very":[234],"practical":[235],"real-situations.":[237]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}