{"id":"https://openalex.org/W2084848593","doi":"https://doi.org/10.1145/1014052.1016922","title":"Document preprocessing for naive Bayes classification and clustering with mixture of multinomials","display_name":"Document preprocessing for naive Bayes classification and clustering with mixture of multinomials","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2084848593","doi":"https://doi.org/10.1145/1014052.1016922","mag":"2084848593"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1016922","doi":"https://doi.org/10.1145/1014052.1016922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016922","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 tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5110057155","display_name":"Dmitry Pavlov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Pavlov","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079821742","display_name":"Ramnath Balasubramanyan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramnath Balasubramanyan","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038597666","display_name":"Shyam Kapur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shyam Kapur","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058763599","display_name":"Jignashu Parikh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignashu Parikh","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":1.1857,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.75811046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9404000043869019,"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":0.9404000043869019,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.04050000011920929,"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/T10028","display_name":"Topic Modeling","score":0.007000000216066837,"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-classifier","display_name":"Naive Bayes classifier","score":0.8119999766349792},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.7699999809265137},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.9789999723434448},{"id":"https://openalex.org/keywords/document-image-preprocessing","display_name":"document preprocessing","score":0.7689999938011169},{"id":"https://openalex.org/keywords/feature-transformation","display_name":"feature transformation","score":0.7829999923706055},{"id":"https://openalex.org/keywords/idf-weighting","display_name":"IDF weighting","score":0.5509999990463257},{"id":"https://openalex.org/keywords/user-queries","display_name":"user queries","score":0.5789999961853027}],"concepts":[{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7609068155288696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464650869369507},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7338966727256775},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5915294289588928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5659522414207458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5519079566001892},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.43160712718963623},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.41038355231285095},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38985615968704224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14988914132118225},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1280326545238495},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10062703490257263},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1014052.1016922","doi":"https://doi.org/10.1145/1014052.1016922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016922","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 tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1539323528","https://openalex.org/W1550206324","https://openalex.org/W1595781024","https://openalex.org/W1966917791","https://openalex.org/W2068405010","https://openalex.org/W2105038653","https://openalex.org/W2140336868","https://openalex.org/W2140785063","https://openalex.org/W2148980227","https://openalex.org/W2492794003","https://openalex.org/W3017143921"],"related_works":["https://openalex.org/W7095730919","https://openalex.org/W2377546166","https://openalex.org/W67881473","https://openalex.org/W7096474089","https://openalex.org/W2181546869","https://openalex.org/W7099529744","https://openalex.org/W7095574003","https://openalex.org/W1565201084","https://openalex.org/W4248570092","https://openalex.org/W1517383656"],"abstract_inverted_index":{"Naive":[0,81],"Bayes":[1,82],"classifier":[2],"has":[3,23,72],"long":[4],"been":[5,25,73],"used":[6],"for":[7],"text":[8,29],"categorization":[9],"tasks.":[10],"Its":[11],"sibling":[12],"from":[13,44],"the":[14,17,33,64,67,78,93,96,100,103,107,126,146,156,160],"unsupervised":[15],"world,":[16],"probabilistic":[18],"mixture":[19],"of":[20,66,80,95,102,109,119,128,159],"multinomial":[21,161],"models,":[22],"likewise":[24],"successfully":[26],"applied":[27],"to":[28,53,76,115,134,142,154],"clustering":[30,125],"problems.":[31],"Despite":[32],"strong":[34,157],"independence":[35],"assumptions":[36,158],"that":[37,148],"these":[38,110,149],"models":[39],"make,":[40],"their":[41],"attractiveness":[42],"come":[43],"low":[45,49],"computational":[46],"cost,":[47],"relatively":[48],"memory":[50],"consumption,":[51],"ability":[52],"handle":[54],"heterogeneous":[55],"features":[56],"and":[57,60,98,112,124],"multiple":[58],"classes,":[59],"often":[61],"competitiveness":[62],"with":[63,152],"top":[65],"line":[68],"models.":[69],"Recently,":[70],"there":[71],"several":[74],"attempts":[75],"alleviate":[77],"problems":[79],"by":[83,92],"performing":[84],"heuristic":[85],"feature":[86],"transformations,":[87],"such":[88],"as":[89],"IDF,":[90],"normalization":[91],"length":[94],"documents":[97],"taking":[99],"logarithms":[101],"counts.":[104],"We":[105],"justify":[106],"use":[108],"techniques":[111],"apply":[113],"them":[114],"two":[116],"problems:":[117],"classification":[118],"products":[120],"in":[121,131],"Yahoo!":[122,135],"Shopping":[123],"vectors":[127],"collocated":[129],"terms":[130],"user":[132],"queries":[133],"Search.":[136],"The":[137],"experimental":[138],"evaluation":[139],"allows":[140],"us":[141],"draw":[143],"conclusions":[144],"about":[145],"promise":[147],"transformations":[150],"carry":[151],"regard":[153],"alleviating":[155],"model.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}