{"id":"https://openalex.org/W2082965028","doi":"https://doi.org/10.1145/564376.564442","title":"Experiments in high-dimensional text categorization","display_name":"Experiments in high-dimensional text categorization","publication_year":2002,"publication_date":"2002-08-11","ids":{"openalex":"https://openalex.org/W2082965028","doi":"https://doi.org/10.1145/564376.564442","mag":"2082965028"},"language":"en","primary_location":{"id":"doi:10.1145/564376.564442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/564376.564442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5056772857","display_name":"Fred J. Damerau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fred J. Damerau","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378754","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0001-6212-4891"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101163155","display_name":"Sholom M. Weiss","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sholom M. Weiss","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035432828","display_name":"Nitin Indurkhya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nitin Indurkhya","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056772857"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.7046,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86155575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"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":0.9965000152587891,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9563000202178955,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9521999955177307,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/categorization","display_name":"Categorization","score":0.8208112120628357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7767910957336426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7193668484687805},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.6866182088851929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283202528953552},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47112298011779785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47056838870048523},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45678457617759705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3817054033279419},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3327468931674957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32723820209503174},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07975363731384277}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8208112120628357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7767910957336426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193668484687805},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.6866182088851929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283202528953552},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47112298011779785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47056838870048523},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45678457617759705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3817054033279419},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3327468931674957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32723820209503174},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07975363731384277},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/564376.564442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/564376.564442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.ust.hk:1783.1-98470","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=0163-5840&rft.volume=&rft.issue=&rft.date=2002&rft.spage=357&rft.aulast=Damerau&rft.aufirst=&rft.atitle=Experiments+in+high-dimensional+text+categorization&rft.title=SIGIR+Forum+%28ACM+Special+Interest+Group+on+Information+Retrieval%29","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2047139419","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2951187577","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173"],"abstract_inverted_index":{"We":[0,29],"present":[1],"results":[2,50,83,92],"for":[3,84,114],"automated":[4],"text":[5,42],"categorization":[6,43],"of":[7,11,21,41,56,71],"the":[8,17,25,31,46,81,85],"Reuters-810000":[9],"collection":[10,20],"news":[12],"stories.":[13],"Our":[14],"experiments":[15],"use":[16],"entire":[18,26],"one-year":[19],"810,000":[22],"stories":[23],"and":[24,36,59],"subject":[27],"index.":[28],"divide":[30],"data":[32],"into":[33],"monthly":[34],"groups":[35],"provide":[37],"an":[38],"initial":[39],"benchmark":[40],"performance":[44,75],"on":[45],"complete":[47],"collection.":[48],"Experimental":[49],"show":[51],"that":[52,101],"efficient":[53],"sparse-feature":[54],"implementations":[55],"linear":[57],"methods":[58],"decision":[60],"trees,":[61],"using":[62],"a":[63,102],"global":[64],"unstemmed":[65],"dictionary,":[66],"can":[67],"readily":[68],"handle":[69],"applications":[70],"this":[72],"size.":[73],"Predictive":[74],"is":[76,99,119],"approximately":[77],"as":[78,80],"strong":[79],"best":[82],"much":[86],"smaller":[87,103],"older":[88],"Reuters":[89],"collections.":[90],"Detailed":[91],"are":[93],"provided":[94],"over":[95],"time":[96,104],"periods.":[97],"It":[98],"shown":[100],"horizon":[105],"does":[106],"not":[107],"diminish":[108],"predictive":[109],"quality,":[110],"implying":[111],"reduced":[112],"demands":[113],"retraining":[115],"when":[116],"sample":[117],"size":[118],"large.":[120]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}