{"id":"https://openalex.org/W1999337483","doi":"https://doi.org/10.1145/502585.502604","title":"Text classification in a hierarchical mixture model for small training sets","display_name":"Text classification in a hierarchical mixture model for small training sets","publication_year":2001,"publication_date":"2001-10-05","ids":{"openalex":"https://openalex.org/W1999337483","doi":"https://doi.org/10.1145/502585.502604","mag":"1999337483"},"language":"en","primary_location":{"id":"doi:10.1145/502585.502604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502585.502604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","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/A5053947885","display_name":"Kristina Toutanova","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristina Toutanova","raw_affiliation_strings":["Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025376488","display_name":"Francine Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francine Chen","raw_affiliation_strings":["Xerox PARC, Palo Alto, CA","Xerox-PARC, Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox PARC, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"Xerox-PARC, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103703111","display_name":"Kris Popat","orcid":null},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kris Popat","raw_affiliation_strings":["Xerox PARC, Palo Alto, CA","Xerox-PARC, Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox PARC, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]},{"raw_affiliation_string":"Xerox-PARC, Palo Alto, CA","institution_ids":["https://openalex.org/I173498003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045413165","display_name":"Thomas Hofmann","orcid":"https://orcid.org/0000-0003-4057-7165"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Hofmann","raw_affiliation_strings":["Brown University, Providence, RI","Brown University, Providence, RI,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Brown University, Providence, RI,","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4672,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95356612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"113"},"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":0.9915000200271606,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9782000184059143,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8125088214874268},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7786563634872437},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6969859004020691},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.5928519368171692},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5593295097351074},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.555229663848877},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5353600978851318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233216285705566},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5065919160842896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4574732780456543},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35869038105010986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35547924041748047},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10502639412879944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125088214874268},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7786563634872437},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6969859004020691},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.5928519368171692},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5593295097351074},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.555229663848877},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5353600978851318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233216285705566},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5065919160842896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4574732780456543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35869038105010986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35547924041748047},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10502639412879944},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/502585.502604","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502585.502604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.6325","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.6325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.parc.xerox.com/istl/members/fchen/papers/CIKM01.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1487445520","https://openalex.org/W1493526108","https://openalex.org/W1523949738","https://openalex.org/W1550206324","https://openalex.org/W1559013041","https://openalex.org/W1572100238","https://openalex.org/W1574901103","https://openalex.org/W1576520375","https://openalex.org/W1597533204","https://openalex.org/W1598746691","https://openalex.org/W1604938182","https://openalex.org/W1620204465","https://openalex.org/W1924689489","https://openalex.org/W1974413746","https://openalex.org/W2005422315","https://openalex.org/W2063862666","https://openalex.org/W2107743791","https://openalex.org/W2139578439","https://openalex.org/W2170654002","https://openalex.org/W2602753196","https://openalex.org/W2911640577","https://openalex.org/W4233135949","https://openalex.org/W6614676750","https://openalex.org/W6634442568"],"related_works":["https://openalex.org/W1967674543","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947"],"abstract_inverted_index":{"Documents":[0],"are":[1,85],"commonly":[2],"categorized":[3],"into":[4],"hierarchies":[5,35],"of":[6,29,51,58,81,89,98,111,127],"topics,":[7],"such":[8],"as":[9],"the":[10,16,41,55,70,82,92,102,105,112],"ones":[11],"maintained":[12],"by":[13,87],"Yahoo!":[14],"and":[15,25,75,104],"Open":[17],"Directory":[18],"project,":[19],"in":[20,44,91,115],"order":[21],"to":[22,39,95,117],"facilitate":[23],"browsing":[24],"other":[26,118],"interactive":[27],"forms":[28],"information":[30],"retrieval.":[31],"In":[32],"addition,":[33],"topic":[34],"can":[36],"be":[37],"utilized":[38],"overcome":[40],"sparseness":[42],"problem":[43],"text":[45],"categorization":[46],"with":[47,123],"a":[48,64,124],"large":[49],"number":[50,126],"categories,":[52],"which":[53,68],"is":[54],"main":[56],"focus":[57],"this":[59],"paper.":[60],"This":[61],"paper":[62],"presents":[63],"hierarchical":[65,77],"mixture":[66],"model":[67],"extends":[69],"standard":[71],"naive":[72],"Bayes":[73],"classifier":[74,114],"previous":[76],"approaches.":[78],"Improved":[79],"estimates":[80],"term":[83],"distributions":[84],"made":[86],"differentiation":[88],"words":[90],"hierarchy":[93],"according":[94],"their":[96],"level":[97],"generality/specificity.":[99],"Experiments":[100],"on":[101,121],"Newsgroups":[103],"Reuters-21578":[106],"dataset":[107],"indicate":[108],"improved":[109],"performance":[110],"proposed":[113],"comparison":[116],"state-of-the-art":[119],"methods":[120],"datasets":[122],"small":[125],"positive":[128],"examples.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}