{"id":"https://openalex.org/W2058089741","doi":"https://doi.org/10.1002/asi.4630260106","title":"A theory of term importance in automatic text analysis","display_name":"A theory of term importance in automatic text analysis","publication_year":1975,"publication_date":"1975-01-01","ids":{"openalex":"https://openalex.org/W2058089741","doi":"https://doi.org/10.1002/asi.4630260106","mag":"2058089741"},"language":"en","primary_location":{"id":"doi:10.1002/asi.4630260106","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.4630260106","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science","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/A5109936506","display_name":"Gerard Salton","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Salton","raw_affiliation_strings":["Department of Computer Science Cornell University Ithaca, New York 14853"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Cornell University Ithaca, New York 14853","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051050164","display_name":"Chul\u2010Su Yang","orcid":"https://orcid.org/0000-0003-4918-961X"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. S. Yang","raw_affiliation_strings":["Department of Computer Science Cornell University Ithaca, New York 14853"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Cornell University Ithaca, New York 14853","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109224736","display_name":"C. Yu","orcid":"https://orcid.org/0009-0007-3659-1788"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"C. T. Yu","raw_affiliation_strings":["Department of Computing Science University of Alberta Edmonton, Alberta, Canada","Department of Computing Science, University of Alberta.Edmonton, Alberta, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science University of Alberta Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta.Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.9135,"has_fulltext":false,"cited_by_count":388,"citation_normalized_percentile":{"value":0.97911612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"26","issue":"1","first_page":"33","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9847999811172485,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9847999811172485,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9300000071525574,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.920799970626831,"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/term","display_name":"Term (time)","score":0.7832884788513184},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6944748759269714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829413771629333},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6029573678970337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5894246697425842},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.577973484992981},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5729584693908691},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.562182605266571},{"id":"https://openalex.org/keywords/automatic-indexing","display_name":"Automatic indexing","score":0.5276445150375366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4955631494522095},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4937301576137543},{"id":"https://openalex.org/keywords/content-analysis","display_name":"Content analysis","score":0.47011056542396545},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4596838653087616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3283880949020386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25828176736831665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23614534735679626}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7832884788513184},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6944748759269714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829413771629333},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6029573678970337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5894246697425842},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.577973484992981},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5729584693908691},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.562182605266571},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.5276445150375366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4955631494522095},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4937301576137543},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.47011056542396545},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4596838653087616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3283880949020386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25828176736831665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23614534735679626},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/asi.4630260106","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.4630260106","pdf_url":null,"source":{"id":"https://openalex.org/S4210220780","display_name":"Journal of the American Society for Information Science","issn_l":"0002-8231","issn":["0002-8231","1097-4571"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science","raw_type":"journal-article"},{"id":"pmh:oai:ecommons.cornell.edu:1813/6048","is_oa":false,"landing_page_url":"https://hdl.handle.net/1813/6048","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"technical report"},{"id":"pmh:oai:null:1813/6048","is_oa":false,"landing_page_url":"http://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR74-208","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"technical report"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1979346010","https://openalex.org/W1982442952","https://openalex.org/W1985697096","https://openalex.org/W1992081792","https://openalex.org/W2003186657","https://openalex.org/W2009190245","https://openalex.org/W2031841382","https://openalex.org/W2075006521","https://openalex.org/W2082729696","https://openalex.org/W2144211451","https://openalex.org/W2165612380","https://openalex.org/W3023595663","https://openalex.org/W4402508796"],"related_works":["https://openalex.org/W204619012","https://openalex.org/W2398073981","https://openalex.org/W2008087111","https://openalex.org/W4247874641","https://openalex.org/W2051392313","https://openalex.org/W2081057833","https://openalex.org/W2025451713","https://openalex.org/W2062327384","https://openalex.org/W2168066506","https://openalex.org/W2023793323"],"abstract_inverted_index":{"Abstract":[0],"A":[1,50],"good":[2],"deal":[3],"of":[4,35,74,84,153],"work":[5],"has":[6],"been":[7],"done":[8],"over":[9],"the":[10,43,59,72,82,91,99,114,151,154],"years":[11],"in":[12,40,62,130],"an":[13],"attempt":[14],"to":[15,70,133],"use":[16],"statistical":[17],"or":[18,143],"probabilistic":[19],"techniques":[20],"as":[21,54],"a":[22,75,85,127],"basis":[23],"for":[24,104],"automatic":[25],"indexing":[26],"and":[27,42,124,138,140],"content":[28,105,131],"analysis.":[29],"(":[30],"1\u201310":[31],")":[32],"Unfortunately,":[33],"many":[34],"these":[36],"methods":[37],"are":[38,47,68,110,148],"lacking":[39],"effectiveness,":[41],"more":[44],"refined":[45],"procedures":[46],"computationally":[48,122],"unattractive.":[49],"new":[51],"technique,":[52],"known":[53],"discrimination":[55,118],"value":[56,83,119],"analysis,":[57],"ranks":[58],"text":[60],"words":[61,109,137],"accordance":[63],"with":[64],"how":[65,89],"well":[66],"they":[67],"able":[69],"discriminate":[71],"documents":[73,96],"collection":[76],"from":[77],"each":[78],"other;":[79],"that":[80],"is,":[81],"term":[86,101],"depends":[87],"on":[88],"much":[90],"average":[92],"separation":[93],"between":[94],"individual":[95],"changes":[97],"when":[98],"given":[100,149],"is":[102,121],"assigned":[103],"identification.":[106],"The":[107,117],"best":[108],"those":[111],"which":[112],"achieve":[113],"greatest":[115],"separation.":[116],"analysis":[120,132],"simple,":[123],"it":[125],"assigns":[126],"specific":[128],"role":[129],"single":[134],"words,":[135],"juxtaposed":[136],"phrases,":[139],"word":[141],"groups":[142],"thesaurus":[144],"categories.":[145],"Experimental":[146],"results":[147],"showing":[150],"effectiveness":[152],"technique.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}