{"id":"https://openalex.org/W2057712948","doi":"https://doi.org/10.1016/s0306-4379(00)00022-3","title":"Rock: A robust clustering algorithm for categorical attributes","display_name":"Rock: A robust clustering algorithm for categorical attributes","publication_year":2000,"publication_date":"2000-07-01","ids":{"openalex":"https://openalex.org/W2057712948","doi":"https://doi.org/10.1016/s0306-4379(00)00022-3","mag":"2057712948"},"language":"en","primary_location":{"id":"doi:10.1016/s0306-4379(00)00022-3","doi":"https://doi.org/10.1016/s0306-4379(00)00022-3","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0306-4379(00)00022-3","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-b","jufo-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/s0306-4379(00)00022-3","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114008024","display_name":"Sudipto Guha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudipto Guha","raw_affiliation_strings":["Stanford University, Stanford, CA 94305, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev R. Rastogi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Bell Laboratories, Murray Hill, NJ 07974, USA","Bell Labs, Murray Hill, NJ 07974, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bell Laboratories, Murray Hill, NJ 07974, USA","institution_ids":[]},{"raw_affiliation_string":"Bell Labs, Murray Hill, NJ 07974, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049064713","display_name":"Kyuseok Shim","orcid":"https://orcid.org/0000-0001-8818-0963","observed_orcids":["https://orcid.org/0000-0001-8818-0963"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuseok Shim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology and Advanced Information Technology Research Center, Taejon 305-701, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology and Advanced Information Technology Research Center, Taejon 305-701, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3410,"currency":"USD","value_usd":3410},"apc_paid":{"value":3410,"currency":"USD","value_usd":3410},"fwci":36.2771,"has_fulltext":false,"cited_by_count":1529,"citation_normalized_percentile":{"value":0.99829954,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":"5","first_page":"345","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.00019999999494757503,"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/T11106","display_name":"Data Management and Algorithms","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variables","display_name":"categorical variables","score":0.6779999732971191},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"hierarchical clustering","score":0.9449999928474426},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7771221399307251},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6759198307991028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6608912944793701},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6330385804176331},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5618994832038879},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5233554244041443},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.4967346787452698},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4820738434791565},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4809828996658325},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4786297380924225},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46681591868400574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4536733627319336},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.44556912779808044},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.43542274832725525},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4342801868915558},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4144597351551056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3865242004394531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25176823139190674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20774853229522705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06498527526855469},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/s0306-4379(00)00022-3","doi":"https://doi.org/10.1016/s0306-4379(00)00022-3","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0306-4379(00)00022-3","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-b","jufo-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.8558","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.8558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.kaist.ac.kr/~shim/is-rock.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.6244","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.6244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dblab.kaist.ac.kr/~shim/icde99-rock.ps.gz","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1016/s0306-4379(00)00022-3","doi":"https://doi.org/10.1016/s0306-4379(00)00022-3","is_oa":true,"landing_page_url":"https://doi.org/10.1016/s0306-4379(00)00022-3","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-b","jufo-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W60856054","https://openalex.org/W142798423","https://openalex.org/W1531368347","https://openalex.org/W1575476631","https://openalex.org/W1587157435","https://openalex.org/W1673310716","https://openalex.org/W1971784203","https://openalex.org/W2080063509","https://openalex.org/W2095897464","https://openalex.org/W2101616188","https://openalex.org/W2112173399","https://openalex.org/W2119885577","https://openalex.org/W2120970098","https://openalex.org/W2752885492","https://openalex.org/W3017143921","https://openalex.org/W4230692091","https://openalex.org/W4235935333","https://openalex.org/W4237841550","https://openalex.org/W6641141775","https://openalex.org/W6645117220","https://openalex.org/W6824323157"],"related_works":["https://openalex.org/W7095212256","https://openalex.org/W7095750493","https://openalex.org/W2047343660","https://openalex.org/W1480386223","https://openalex.org/W3621232","https://openalex.org/W175060316","https://openalex.org/W2809995938","https://openalex.org/W2788737710","https://openalex.org/W7095589623","https://openalex.org/W92191237"],"abstract_inverted_index":{"Clustering,":[0],"in":[1,10,26,36,45,129],"data":[2,34,56,99,163,173],"mining,":[3],"is":[4,136],"useful":[5],"to":[6,28,91,122,144,165],"discover":[7],"distribution":[8],"patterns":[9],"the":[11,30,37,93,137,167],"underlying":[12],"data.":[13],"Clustering":[14],"algorithms":[15,54,67],"usually":[16],"employ":[17],"a":[18,86,96,103,132],"distance":[19],"metric":[20],"based":[21],"(e.g.,":[22],"euclidean)":[23],"similarity":[24,124],"measure":[25,92],"order":[27],"partition":[29,39],"database":[31],"such":[32],"that":[33,64,68,109,126,180],"points":[35,44,72],"same":[38],"are":[40,75,127],"more":[41],"similar":[42],"than":[43,188],"different":[46],"partitions.":[47],"In":[48,142],"this":[49],"paper,":[50],"we":[51,84,151],"study":[52,156],"clustering":[53,66,74,106],"for":[55,73,78,149],"with":[57,157,174],"boolean":[58,79],"and":[59,80,112],"categorical":[60,81,175],"attributes.":[61,82],"We":[62,101],"show":[63],"traditional":[65,189],"use":[69],"distances":[70,114],"between":[71,95],"not":[76,113,182],"appropriate":[77],"Instead,":[83],"propose":[85],"novel":[87],"concept":[88],"of":[89,98,140,169],"links":[90,111],"similarity/proximity":[94],"pair":[97],"points.":[100],"develop":[102],"robust":[104],"hierarchical":[105],"algorithm":[107],"ROCK":[108,181],"employs":[110],"when":[115],"merging":[116],"clusters.":[117],"Our":[118],"methods":[119],"naturally":[120],"extend":[121],"non-metric":[123],"measures":[125],"relevant":[128],"situations":[130],"where":[131],"domain":[133],"expert/similarity":[134],"table":[135],"only":[138,183],"source":[139],"knowledge.":[141],"addition":[143],"presenting":[145],"detailed":[146],"complexity":[147],"results":[148],"ROCK,":[150],"also":[152,193],"conduct":[153],"an":[154],"experimental":[155],"real-life":[158],"as":[159,161],"well":[160],"synthetic":[162],"sets":[164],"demonstrate":[166],"effectiveness":[168],"our":[170,177],"techniques.":[171],"For":[172],"attributes,":[176],"findings":[178],"indicate":[179],"generates":[184],"better":[185],"quality":[186],"clusters":[187],"algorithms,":[190],"but":[191],"it":[192],"exhibits":[194],"good":[195],"scalability":[196],"properties.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":59},{"year":2022,"cited_by_count":54},{"year":2021,"cited_by_count":63},{"year":2020,"cited_by_count":66},{"year":2019,"cited_by_count":55},{"year":2018,"cited_by_count":56},{"year":2017,"cited_by_count":69},{"year":2016,"cited_by_count":55},{"year":2015,"cited_by_count":76},{"year":2014,"cited_by_count":60},{"year":2013,"cited_by_count":79},{"year":2012,"cited_by_count":90}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}