{"id":"https://openalex.org/W4206655101","doi":"https://doi.org/10.1007/s10791-021-09401-8","title":"Measurement of clustering effectiveness for document collections","display_name":"Measurement of clustering effectiveness for document collections","publication_year":2022,"publication_date":"2022-01-10","ids":{"openalex":"https://openalex.org/W4206655101","doi":"https://doi.org/10.1007/s10791-021-09401-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-021-09401-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-021-09401-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-021-09401-8.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10791-021-09401-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102859794","display_name":"Meng Yuan","orcid":"https://orcid.org/0000-0002-6291-6896"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Meng Yuan","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Parkville, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6622-032X","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pauline Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pauline Lin","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041495909"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":{"value":3390,"currency":"USD","value_usd":3390},"apc_paid":{"value":3390,"currency":"USD","value_usd":3390},"fwci":1.6691,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8566986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"25","issue":"3","first_page":"239","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T10637","display_name":"Advanced Clustering Algorithms Research","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/T11106","display_name":"Data Management and Algorithms","score":0.9965999722480774,"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/cluster-analysis","display_name":"Cluster analysis","score":0.9119495749473572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7393091917037964},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7204756140708923},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6464778184890747},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.6128433346748352},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6085781455039978},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5335545539855957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5147449970245361},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4944627285003662},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4678742587566376},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.44807058572769165},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4407501518726349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41467660665512085},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3628285527229309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254010081291199},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06102931499481201}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9119495749473572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393091917037964},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7204756140708923},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6464778184890747},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.6128433346748352},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6085781455039978},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5335545539855957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5147449970245361},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4944627285003662},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4678742587566376},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.44807058572769165},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4407501518726349},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41467660665512085},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3628285527229309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254010081291199},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06102931499481201},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10791-021-09401-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-021-09401-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-021-09401-8.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/308113","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-021-09401-8.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1007/s10791-021-09401-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-021-09401-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-021-09401-8.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval Journal","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206655101.pdf","grobid_xml":"https://content.openalex.org/works/W4206655101.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W35739717","https://openalex.org/W1489608363","https://openalex.org/W1546703457","https://openalex.org/W1673310716","https://openalex.org/W1959178355","https://openalex.org/W1973897992","https://openalex.org/W1975583660","https://openalex.org/W1985059878","https://openalex.org/W1987384987","https://openalex.org/W1987971958","https://openalex.org/W1990368529","https://openalex.org/W1990388042","https://openalex.org/W1995450389","https://openalex.org/W1996881001","https://openalex.org/W1998032016","https://openalex.org/W1998871699","https://openalex.org/W2000117996","https://openalex.org/W2011430131","https://openalex.org/W2013029404","https://openalex.org/W2036295879","https://openalex.org/W2041565863","https://openalex.org/W2042980227","https://openalex.org/W2046878543","https://openalex.org/W2051224630","https://openalex.org/W2061198046","https://openalex.org/W2062723323","https://openalex.org/W2070377439","https://openalex.org/W2070412788","https://openalex.org/W2075893676","https://openalex.org/W2081771622","https://openalex.org/W2086662461","https://openalex.org/W2095308899","https://openalex.org/W2098418076","https://openalex.org/W2100738695","https://openalex.org/W2112242578","https://openalex.org/W2121973001","https://openalex.org/W2130395434","https://openalex.org/W2131912994","https://openalex.org/W2132876818","https://openalex.org/W2136635436","https://openalex.org/W2138662031","https://openalex.org/W2140870987","https://openalex.org/W2142489247","https://openalex.org/W2155194165","https://openalex.org/W2163075838","https://openalex.org/W2168400688","https://openalex.org/W2170111518","https://openalex.org/W2171144050","https://openalex.org/W2174706414","https://openalex.org/W2461435072","https://openalex.org/W2479915852","https://openalex.org/W2538688051","https://openalex.org/W2887229810","https://openalex.org/W2903590249","https://openalex.org/W2906947843","https://openalex.org/W2962763150","https://openalex.org/W3149550307","https://openalex.org/W4241122026","https://openalex.org/W4245235621","https://openalex.org/W4249737388","https://openalex.org/W4255459561","https://openalex.org/W7043762925"],"related_works":["https://openalex.org/W2622412490","https://openalex.org/W2160785859","https://openalex.org/W2183326556","https://openalex.org/W4285159010","https://openalex.org/W2891223594","https://openalex.org/W2954628966","https://openalex.org/W1997571094","https://openalex.org/W2387287989","https://openalex.org/W4385594911","https://openalex.org/W2101926443"],"abstract_inverted_index":{"Abstract":[0],"Clustering":[1],"of":[2,5,23,39,51,65,77,104,137],"the":[3,15,57,74,78,135,194],"contents":[4],"a":[6,37,49,96,102,184],"document":[7,42],"corpus":[8],"is":[9,34,81,179,190],"used":[10,35,132],"to":[11,21,28,56,100,109,133,146,165,182],"create":[12],"sub-corpora":[13],"with":[14,114],"intention":[16],"that":[17,25,83,127,142,157,161],"they":[18,155],"are":[19,26],"expected":[20],"consist":[22],"documents":[24,125],"related":[27],"each":[29],"other.":[30],"However,":[31],"while":[32],"clustering":[33,84,98,111,143,159,178,204],"in":[36,41,70,168],"variety":[38,103],"ways":[40],"applications":[43],"such":[44],"as":[45,193],"information":[46,129,175],"retrieval,":[47],"and":[48,107,139],"range":[50],"methods":[52],"have":[53,162,183],"been":[54,61,163],"applied":[55],"task,":[58],"there":[59],"has":[60],"relatively":[62],"little":[63],"exploration":[64],"how":[66],"well":[67],"it":[68,80],"works":[69],"practice.":[71],"Indeed,":[72],"given":[73],"high":[75],"dimensionality":[76],"data":[79],"possible":[82],"may":[85],"not":[86,172],"always":[87],"produce":[88],"meaningful":[89],"outcomes.":[90],"In":[91],"this":[92],"paper":[93],"we":[94],"use":[95],"well-known":[97],"method":[99],"explore":[101],"techniques,":[105],"existing":[106],"novel,":[108],"measure":[110],"effectiveness.":[112],"Results":[113],"our":[115,197],"new,":[116],"extrinsic":[117],"techniques":[118,160,199],"based":[119],"on":[120,187],"relevance":[121],"judgements":[122],"or":[123],"retrieved":[124],"demonstrate":[126],"retrieval-based":[128],"can":[130,144,200],"be":[131,166],"assess":[134],"quality":[136],"clustering,":[138],"also":[140],"show":[141,156,196],"succeed":[145],"some":[147],"extent":[148],"at":[149],"gathering":[150],"together":[151],"similar":[152],"material.":[153],"Further,":[154],"intrinsic":[158],"shown":[164],"informative":[167],"other":[169],"domains":[170],"do":[171],"work":[173],"for":[174],"retrieval.":[176],"Whether":[177],"sufficiently":[180],"effective":[181],"significant":[185],"impact":[186],"practical":[188],"retrieval":[189],"unclear,":[191],"but":[192],"results":[195],"measurement":[198],"effectively":[201],"distinguish":[202],"between":[203],"methods.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}