{"id":"https://openalex.org/W2096468639","doi":"https://doi.org/10.1007/s007999900025","title":"A probabilistic justification for using tf\u00d7idf term weighting in information retrieval","display_name":"A probabilistic justification for using tf\u00d7idf term weighting in information retrieval","publication_year":2000,"publication_date":"2000-08-01","ids":{"openalex":"https://openalex.org/W2096468639","doi":"https://doi.org/10.1007/s007999900025","mag":"2096468639"},"language":"en","primary_location":{"id":"doi:10.1007/s007999900025","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007999900025","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","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/A5108167267","display_name":"Djoerd Hiemstra","orcid":"https://orcid.org/0000-0003-4967-2900"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL","PK"],"is_corresponding":true,"raw_author_name":"Djoerd Hiemstra","raw_affiliation_strings":["Centre for Telematics and Information Technology, University of Twente, The Netherlands;","[Centre for Telematics and Information Technology, University of Twente, The Netherlands]"],"affiliations":[{"raw_affiliation_string":"Centre for Telematics and Information Technology, University of Twente, The Netherlands;","institution_ids":["https://openalex.org/I94624287"]},{"raw_affiliation_string":"[Centre for Telematics and Information Technology, University of Twente, The Netherlands]","institution_ids":["https://openalex.org/I1323252656"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108167267"],"corresponding_institution_ids":["https://openalex.org/I1323252656","https://openalex.org/I94624287"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":11.1327,"has_fulltext":false,"cited_by_count":184,"citation_normalized_percentile":{"value":0.97955819,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"3","issue":"2","first_page":"131","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.8579344153404236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8275797963142395},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7445019483566284},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7439521551132202},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.7295323610305786},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5918421149253845},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.5556226968765259},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5205262899398804},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.47685348987579346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45679524540901184},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4539773464202881}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8579344153404236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275797963142395},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7445019483566284},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7439521551132202},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.7295323610305786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5918421149253845},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.5556226968765259},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5205262899398804},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.47685348987579346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45679524540901184},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4539773464202881},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s007999900025","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007999900025","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/ae8124b1-5b56-4019-9dce-b54225f36e53","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/ae8124b1-5b56-4019-9dce-b54225f36e53","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hiemstra, D 2000, 'A probabilistic justification for using tf.idf term weighting in information retrieval', International journal on digital libraries, vol. 3, no. 2, pp. 131-139. https://doi.org/10.1007/s007999900025","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/228471","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/228471","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal on Digital Libraries, 3, 2, pp. 131-139","raw_type":"Article / Letter to editor"},{"id":"pmh:oai:ris.utwente.nl:publications/ae8124b1-5b56-4019-9dce-b54225f36e53","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W118165685","https://openalex.org/W158516103","https://openalex.org/W1513915383","https://openalex.org/W1540124269","https://openalex.org/W1548980684","https://openalex.org/W1549461845","https://openalex.org/W1603407985","https://openalex.org/W1891236516","https://openalex.org/W1953655781","https://openalex.org/W1978394996","https://openalex.org/W1988711048","https://openalex.org/W2001664274","https://openalex.org/W2014415866","https://openalex.org/W2043909051","https://openalex.org/W2075006521","https://openalex.org/W2093390569","https://openalex.org/W2177725428","https://openalex.org/W2325227998","https://openalex.org/W3015934416","https://openalex.org/W4206765718","https://openalex.org/W4251326898"],"related_works":["https://openalex.org/W4281569536","https://openalex.org/W2171473894","https://openalex.org/W2741230576","https://openalex.org/W2372355498","https://openalex.org/W1513915383","https://openalex.org/W2057062109","https://openalex.org/W2038542535","https://openalex.org/W3136891595","https://openalex.org/W2349007695","https://openalex.org/W4254087122"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
