{"id":"https://openalex.org/W2033681837","doi":"https://doi.org/10.1007/s10791-011-9163-y","title":"Improving document clustering using Okapi BM25 feature weighting","display_name":"Improving document clustering using Okapi BM25 feature weighting","publication_year":2011,"publication_date":"2011-02-19","ids":{"openalex":"https://openalex.org/W2033681837","doi":"https://doi.org/10.1007/s10791-011-9163-y","mag":"2033681837"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-011-9163-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-011-9163-y","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"Information Retrieval","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/A5009284826","display_name":"John S. Whissell","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"John S. Whissell","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada","David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037737168","display_name":"Charles L. A. Clarke","orcid":"https://orcid.org/0000-0001-8178-9194"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Charles L. A. Clarke","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada","David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada N2L 3G1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, N2L 3G1, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, Canada N2L 3G1","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009284826"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":4.1863,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9507507,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"14","issue":"5","first_page":"466","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.996399998664856,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9179086685180664},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.784795880317688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6759085655212402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600832104682922},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5306808948516846},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5305604934692383},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.49609455466270447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4339100122451782},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4332771897315979}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.9179086685180664},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.784795880317688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759085655212402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600832104682922},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5306808948516846},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5305604934692383},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.49609455466270447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4339100122451782},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4332771897315979},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-011-9163-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-011-9163-y","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"Information Retrieval","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1493454437","https://openalex.org/W1507051419","https://openalex.org/W1546703457","https://openalex.org/W1612003148","https://openalex.org/W1651093245","https://openalex.org/W1970544520","https://openalex.org/W1971318281","https://openalex.org/W1992419399","https://openalex.org/W2011272347","https://openalex.org/W2013029404","https://openalex.org/W2022006917","https://openalex.org/W2025942372","https://openalex.org/W2032328503","https://openalex.org/W2032443316","https://openalex.org/W2047491155","https://openalex.org/W2060314721","https://openalex.org/W2081980673","https://openalex.org/W2087962968","https://openalex.org/W2120103492","https://openalex.org/W2121947440","https://openalex.org/W2127172217","https://openalex.org/W2132914434","https://openalex.org/W2150593711","https://openalex.org/W2165874743","https://openalex.org/W2294798173","https://openalex.org/W2999729612","https://openalex.org/W3125934771","https://openalex.org/W3139328003","https://openalex.org/W4231336072","https://openalex.org/W4233135949","https://openalex.org/W4285719527","https://openalex.org/W4299835794","https://openalex.org/W6628905179","https://openalex.org/W6637231022","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2276271130","https://openalex.org/W2367393702","https://openalex.org/W2283145973","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
