{"id":"https://openalex.org/W2087173123","doi":"https://doi.org/10.1002/asi.4630260504","title":"A probabilistic approach to automatic keyword indexing. Part II. An algorithm for probabilistic indexing","display_name":"A probabilistic approach to automatic keyword indexing. Part II. An algorithm for probabilistic indexing","publication_year":1975,"publication_date":"1975-09-01","ids":{"openalex":"https://openalex.org/W2087173123","doi":"https://doi.org/10.1002/asi.4630260504","mag":"2087173123"},"language":"en","primary_location":{"id":"doi:10.1002/asi.4630260504","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.4630260504","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/A5056752791","display_name":"Stephen P. Harter","orcid":null},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephen P. Harter","raw_affiliation_strings":["Library Science/Audiovisual Program (FAO 186) University of South Florida Tampa, FL 33620"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Library Science/Audiovisual Program (FAO 186) University of South Florida Tampa, FL 33620","institution_ids":["https://openalex.org/I2613432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056752791"],"corresponding_institution_ids":["https://openalex.org/I2613432"],"apc_list":null,"apc_paid":null,"fwci":1.3628,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.87149431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"5","first_page":"280","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8159112334251404},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.792817234992981},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7553447484970093},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.6373209357261658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6369167566299438},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.5794457197189331},{"id":"https://openalex.org/keywords/automatic-indexing","display_name":"Automatic indexing","score":0.566788375377655},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.4488348662853241},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41918280720710754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.404496431350708},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38201647996902466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3229760527610779},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.31689444184303284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.315548300743103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2808598279953003}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8159112334251404},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.792817234992981},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7553447484970093},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.6373209357261658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6369167566299438},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.5794457197189331},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.566788375377655},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.4488348662853241},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41918280720710754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.404496431350708},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38201647996902466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3229760527610779},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31689444184303284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.315548300743103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2808598279953003},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/asi.4630260504","is_oa":false,"landing_page_url":"https://doi.org/10.1002/asi.4630260504","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W132056723","https://openalex.org/W1982442952","https://openalex.org/W1985697096","https://openalex.org/W2034701578","https://openalex.org/W2038925774","https://openalex.org/W2042432758","https://openalex.org/W2049342053","https://openalex.org/W2049870103","https://openalex.org/W2059782624","https://openalex.org/W2064523138","https://openalex.org/W2074122739","https://openalex.org/W2075006521","https://openalex.org/W2078857984","https://openalex.org/W2080068076","https://openalex.org/W2082729696","https://openalex.org/W2121300685","https://openalex.org/W2143695058","https://openalex.org/W2144211451","https://openalex.org/W2153890685","https://openalex.org/W2163484262","https://openalex.org/W4300038597"],"related_works":["https://openalex.org/W204619012","https://openalex.org/W2398073981","https://openalex.org/W4247874641","https://openalex.org/W2051392313","https://openalex.org/W2081057833","https://openalex.org/W2139991891","https://openalex.org/W2025451713","https://openalex.org/W2062327384","https://openalex.org/W2168066506","https://openalex.org/W2008087111"],"abstract_inverted_index":{"Abstract":[0],"In":[1,53],"Part":[2,57],"I":[3],"of":[4,9,18,27,32,59,65,72,75,85,96],"this":[5],"study,*":[6],"a":[7,16,39,62,83],"mixture":[8],"two":[10],"Poisson":[11],"distributions":[12],"was":[13,51],"examined":[14],"as":[15,126],"model":[17,29,64,77],"specialty":[19,45],"word":[20],"distribution.":[21],"Formulas":[22],"expressing":[23],"the":[24,28,49,54,60,73,76,93,124,128],"three":[25],"parameters":[26],"in":[30,98,123],"terms":[31],"empirical":[33],"frequency":[34],"statistics":[35],"were":[36],"derived,":[37],"and":[38,70,104],"statistical":[40],"measure":[41,84,89,101,117],"intended":[42,90],"to":[43,91,107,112],"identify":[44],"words,":[46],"consistent":[47],"with":[48],"model,":[50],"proposed.":[52],"present":[55],"paper,":[56],"II":[58],"study,":[61],"probabilistic":[63],"keyword":[66],"indexing":[67],"is":[68,87,102,105],"outlined,":[69],"some":[71],"consequences":[74],"are":[78],"examined.":[79],"An":[80],"algorithm":[81],"defining":[82],"indexability":[86],"developed\u2010a":[88],"reflect":[92],"relative":[94],"significance":[95],"words":[97],"documents.":[99],"The":[100],"evaluated":[103],"found":[106],"consistently":[108],"produce":[109],"indexes":[110],"superior":[111],"those":[113],"produced":[114],"by":[115],"another":[116],"which":[118],"had":[119],"previously":[120],"been":[121],"identified":[122],"literature":[125],"producing":[127],"best":[129],"results.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}