{"id":"https://openalex.org/W1967854631","doi":"https://doi.org/10.1142/s0218488503001977","title":"UNCERTAINTY AND TERM SELECTION IN TEXT CATEGORIZATION","display_name":"UNCERTAINTY AND TERM SELECTION IN TEXT CATEGORIZATION","publication_year":2003,"publication_date":"2003-02-01","ids":{"openalex":"https://openalex.org/W1967854631","doi":"https://doi.org/10.1142/s0218488503001977","mag":"1967854631"},"language":"en","primary_location":{"id":"doi:10.1142/s0218488503001977","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218488503001977","pdf_url":null,"source":{"id":"https://openalex.org/S69518169","display_name":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","issn_l":"0218-4885","issn":["0218-4885","1793-6411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems","raw_type":"journal-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/A5109893510","display_name":"Charles M. Peters","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"CHARLES M. E. E. PETERS","raw_affiliation_strings":["Department of Computer Science,  University of Nijmegen, Nijmegen, The Netherlands","Department of Computer Science, University of Nijmegen, Nijmegen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science,  University of Nijmegen, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Department of Computer Science, University of Nijmegen, Nijmegen, the Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032872149","display_name":"C. H. A. Koster","orcid":"https://orcid.org/0009-0000-3393-6110"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"CORNELIS H. A. KOSTER","raw_affiliation_strings":["Department of Computer Science,  University of Nijmegen, Nijmegen, The Netherlands","Department of Computer Science, University of Nijmegen, Nijmegen, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science,  University of Nijmegen, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Department of Computer Science, University of Nijmegen, Nijmegen, the Netherlands","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4065,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84540795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"11","issue":"01","first_page":"115","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9889000058174133,"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/categorization","display_name":"Categorization","score":0.8734374642372131},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.8247799873352051},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7583550810813904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6569145321846008},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6239563822746277},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5375968813896179},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4940793812274933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715350270271301},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4301375448703766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.398939847946167},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3957274258136749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3805784285068512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3567247688770294},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20090195536613464},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.07197844982147217},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06279504299163818}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8734374642372131},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.8247799873352051},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7583550810813904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6569145321846008},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6239563822746277},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5375968813896179},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4940793812274933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715350270271301},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4301375448703766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.398939847946167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3957274258136749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3805784285068512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3567247688770294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20090195536613464},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.07197844982147217},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06279504299163818},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218488503001977","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218488503001977","pdf_url":null,"source":{"id":"https://openalex.org/S69518169","display_name":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","issn_l":"0218-4885","issn":["0218-4885","1793-6411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1487855083","https://openalex.org/W1557757161","https://openalex.org/W1762357721","https://openalex.org/W1813610639","https://openalex.org/W1969572066","https://openalex.org/W2001664274","https://openalex.org/W2060476676","https://openalex.org/W2064580901","https://openalex.org/W2078206416","https://openalex.org/W2094934653","https://openalex.org/W2102800374","https://openalex.org/W2118020653","https://openalex.org/W2164547069","https://openalex.org/W2435251607","https://openalex.org/W6676455310"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2078570174","https://openalex.org/W2035261173","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2138922887"],"abstract_inverted_index":{"This":[0,72,130],"paper":[1],"discusses":[2],"the":[3,13,24,35,65,90,99,105,109,125,135,142],"notion":[4],"of":[5,18,26,31,37,48,92,101,118,124,138,145],"Uncertainty,":[6],"which":[7,61],"has":[8],"a":[9,53,116,121],"prominent":[10],"place":[11],"in":[12,41,50,67,98,154],"theory":[14],"and":[15,40,81,95,111,141],"experimental":[16],"practice":[17],"modern":[19],"Physics.":[20],"It":[21],"argues":[22],"that":[23,133],"awareness":[25],"Uncertainty":[27,49,66],"may":[28],"also":[29],"be":[30,149],"tremendous":[32],"importance":[33],"to":[34,75,115],"field":[36],"Information":[38],"Retrieval,":[39],"particular":[42],"Text":[43,51,155],"Categorization.":[44,156],"As":[45],"an":[46,87],"application":[47],"Categorization,":[52],"new":[54],"criterion":[55,73],"for":[56,151],"Term":[57,68,152],"Selection":[58,153],"is":[59,62],"described,":[60],"based":[63],"on":[64],"Frequency":[69],"across":[70],"categories.":[71],"allows":[74],"distinguish":[76],"between":[77],"low-quality":[78],"(or":[79],"\"noisy\")":[80],"high-quality":[82],"(\"stiff\")":[83],"terms.":[84],"We":[85],"describe":[86],"experiment":[88,106],"investigating":[89],"effect":[91],"eliminating":[93],"noisy":[94,139],"stiff":[96,146],"terms":[97,140,147],"context":[100],"text":[102],"classification.":[103],"In":[104],"we":[107],"applied":[108],"Rocchio":[110],"Winnow":[112],"classification":[113],"algorithms":[114],"collection":[117],"newspaper":[119],"items,":[120],"mono-classified":[122],"subset":[123],"well-known":[126],"Reuters":[127],"21578":[128],"corpus.":[129],"investigation":[131],"shows":[132],"both":[134],"local":[136],"elimination":[137,144],"global":[143],"can":[148],"used":[150]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
