{"id":"https://openalex.org/W2064580901","doi":"https://doi.org/10.1145/290941.290970","title":"Distributional clustering of words for text classification","display_name":"Distributional clustering of words for text classification","publication_year":1998,"publication_date":"1998-08-01","ids":{"openalex":"https://openalex.org/W2064580901","doi":"https://doi.org/10.1145/290941.290970","mag":"2064580901"},"language":"en","primary_location":{"id":"doi:10.1145/290941.290970","doi":"https://doi.org/10.1145/290941.290970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/290941.290970","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2064580901"],"child_works_count":0,"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":null,"display_name":"L. Douglas Baker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Douglas Baker","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Just Research 4616 Henry Street, Pittsburgh, PA","School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Just Research 4616 Henry Street, Pittsburgh, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Just Research 4616 Henry Street, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Just Research 4616 Henry Street, Pittsburgh, PA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103424470","display_name":"Andrew Kachites McCallum","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Kachites McCallum","raw_affiliation_strings":["Just Research 4616 Henry Street, Pittsburgh, PA and School of Computer Science, Carnegie Mellon University, Pittsburgh, PA","Just Research, 4616 Henry Street, Pittsburgh, PA and School of Computer Science, Carnegie Mellon University, Pittsburgh, PA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Just Research 4616 Henry Street, Pittsburgh, PA and School of Computer Science, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Just Research, 4616 Henry Street, Pittsburgh, PA and School of Computer Science, Carnegie Mellon University, Pittsburgh, PA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":13.8303,"has_fulltext":false,"cited_by_count":678,"citation_normalized_percentile":{"value":0.99304561,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0006000000284984708,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.00019999999494757503,"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/text-classification","display_name":"text classification","score":0.8029999732971191},{"id":"https://openalex.org/keywords/document-classification","display_name":"document classification","score":0.8069999814033508},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.8889999985694885},{"id":"https://openalex.org/keywords/word-clustering","display_name":"word clustering","score":0.847000002861023},{"id":"https://openalex.org/keywords/latent-semantic-indexing","display_name":"latent semantic indexing","score":0.6710000038146973},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7570000290870667},{"id":"https://openalex.org/keywords/unsupervised-clustering","display_name":"unsupervised clustering","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6880045533180237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6414927244186401},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5509964227676392},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.5107010006904602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30963966250419617}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/290941.290970","doi":"https://doi.org/10.1145/290941.290970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/290941.290970","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.7488","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.7488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.justresearch.com/publications/clustering-sigir98/clustering-sigir98.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.8379","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.8379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ims.uni-stuttgart.de/~riezler/TEACHING/clustering-papers/BMcC98.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.591.6845","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.591.6845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.cs.swarthmore.edu/~richardw/papers/baker1998-distributional.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1493526108","https://openalex.org/W1507029541","https://openalex.org/W1513366687","https://openalex.org/W1550206324","https://openalex.org/W1840338487","https://openalex.org/W1849729440","https://openalex.org/W1970974276","https://openalex.org/W2089185211","https://openalex.org/W2095958485","https://openalex.org/W2096152098","https://openalex.org/W2098750402","https://openalex.org/W2099111195","https://openalex.org/W2109293916","https://openalex.org/W2121227244","https://openalex.org/W2122111042","https://openalex.org/W2127314673","https://openalex.org/W2138575161","https://openalex.org/W2140785063","https://openalex.org/W2147152072","https://openalex.org/W2167044614","https://openalex.org/W2435251607","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2921497846","https://openalex.org/W2060683726","https://openalex.org/W7096308314","https://openalex.org/W1572477201","https://openalex.org/W2104421947","https://openalex.org/W1488519867","https://openalex.org/W2155942458","https://openalex.org/W7095681379","https://openalex.org/W1730404227","https://openalex.org/W2107068745"],"abstract_inverted_index":{"This":[0,12],"paper":[1],"describes":[2],"the":[3,20,46,72,127],"application":[4],"of":[5,22,78,126],"Distributional":[6],"Clustering":[7],"[20]":[8],"to":[9,44],"document":[10,56],"classification.":[11],"approach":[13],"clusters":[14],"words":[15],"into":[16],"groups":[17],"based":[18],"on":[19,62],"distribution":[21],"class":[23],"labels":[24],"associated":[25],"with":[26],"each":[27],"word.":[28],"Thus,":[29],"unlike":[30],"some":[31],"other":[32],"unsupervised":[33],"dimensionalityreduction":[34],"techniques,":[35],"such":[36],"as":[37],"Latent":[38,87],"Semantic":[39,88],"Indexing,":[40],"we":[41,69],"are":[42],"able":[43],"compress":[45],"feature":[47,73,94,102],"space":[48],"much":[49],"more":[50],"aggressively,":[51],"while":[52],"still":[53],"maintaining":[54],"high":[55],"classification":[57,116,119],"accuracy.":[58],"Experimental":[59],"results":[60,113],"obtained":[61],"three":[63,76],"real-world":[64],"data":[65],"sets":[66],"show":[67,107],"that":[68,108],"can":[70],"reduce":[71],"dimensionality":[74],"by":[75,96],"orders":[77],"magnitude":[79],"and":[80],"lose":[81],"only":[82],"2%":[83],"accuracy---significantly":[84],"better":[85],"than":[86],"Indexing":[89],"[6],":[90],"class-based":[91],"clustering":[92,111],"[1],":[93],"selection":[95,103],"mutual":[97],"information":[98],"[23],":[99],"or":[100],"Markov-blanket-based":[101],"[13].":[104],"We":[105],"also":[106],"less":[109],"aggressive":[110],"sometimes":[112],"in":[114],"improved":[115],"accuracy":[117],"over":[118],"without":[120],"clustering.":[121],"1":[122],"Introduction":[123],"The":[124],"popularity":[125],"Internet":[128],"has":[129],"caused":[130],"an":[131],"exponent...":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":29},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":53},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":29}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}