{"id":"https://openalex.org/W2148524305","doi":"https://doi.org/10.14778/1687627.1687771","title":"Framework for evaluating clustering algorithms in duplicate detection","display_name":"Framework for evaluating clustering algorithms in duplicate detection","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2148524305","doi":"https://doi.org/10.14778/1687627.1687771","mag":"2148524305"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687771","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687771","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5068065546","display_name":"Oktie Hassanzadeh","orcid":"https://orcid.org/0000-0001-5307-9857"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Oktie Hassanzadeh","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061267570","display_name":"Fei Chiang","orcid":"https://orcid.org/0000-0003-4128-8074"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fei Chiang","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079946759","display_name":"Hyun\u2010Chul Lee","orcid":"https://orcid.org/0000-0002-2466-4667"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun Chul Lee","raw_affiliation_strings":["Thoora Inc"],"affiliations":[{"raw_affiliation_string":"Thoora Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068065546"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":10.4147,"has_fulltext":false,"cited_by_count":231,"citation_normalized_percentile":{"value":0.98422368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"1282","last_page":"1293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"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":0.9894999861717224,"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/computer-science","display_name":"Computer science","score":0.7946337461471558},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.75211501121521},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7515887022018433},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7062035202980042},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.4935997724533081},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44585704803466797},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44584739208221436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3133549094200134},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25897204875946045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946337461471558},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.75211501121521},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7515887022018433},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7062035202980042},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.4935997724533081},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44585704803466797},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44584739208221436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3133549094200134},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25897204875946045},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687771","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687771","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.8708","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.8708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-1025.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W99972189","https://openalex.org/W192724328","https://openalex.org/W254113056","https://openalex.org/W1488413262","https://openalex.org/W1497709229","https://openalex.org/W1514151181","https://openalex.org/W1522029489","https://openalex.org/W1536860849","https://openalex.org/W1564399566","https://openalex.org/W1585610988","https://openalex.org/W1602412127","https://openalex.org/W1604983895","https://openalex.org/W1612155886","https://openalex.org/W1646278814","https://openalex.org/W1783384641","https://openalex.org/W1971784203","https://openalex.org/W1976208596","https://openalex.org/W1985875030","https://openalex.org/W1992419399","https://openalex.org/W1995541812","https://openalex.org/W1999478155","https://openalex.org/W2002531683","https://openalex.org/W2017732166","https://openalex.org/W2024605621","https://openalex.org/W2030724586","https://openalex.org/W2034331023","https://openalex.org/W2035890032","https://openalex.org/W2064244056","https://openalex.org/W2090359754","https://openalex.org/W2091858563","https://openalex.org/W2096554081","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2108991785","https://openalex.org/W2109682749","https://openalex.org/W2113415503","https://openalex.org/W2119057313","https://openalex.org/W2121564430","https://openalex.org/W2127675794","https://openalex.org/W2129066856","https://openalex.org/W2129598390","https://openalex.org/W2138745909","https://openalex.org/W2146081992","https://openalex.org/W2148019918","https://openalex.org/W2149342630","https://openalex.org/W2153233077","https://openalex.org/W2155074104","https://openalex.org/W2167372977","https://openalex.org/W2309226206","https://openalex.org/W2319660501","https://openalex.org/W2403325993","https://openalex.org/W2752885492","https://openalex.org/W2801345297","https://openalex.org/W2895397838","https://openalex.org/W2914959486","https://openalex.org/W3014094413","https://openalex.org/W3145128584","https://openalex.org/W4213060883","https://openalex.org/W6676613663","https://openalex.org/W6770641979","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W12581771","https://openalex.org/W2766145069","https://openalex.org/W3003602898","https://openalex.org/W2515214618","https://openalex.org/W2547510008","https://openalex.org/W2313358680","https://openalex.org/W2736204053","https://openalex.org/W2752889248","https://openalex.org/W1972694312","https://openalex.org/W2364921833"],"abstract_inverted_index":{"The":[0],"presence":[1],"of":[2,32,66,85,89,143],"duplicate":[3,136],"records":[4,39],"is":[5,27,107],"a":[6,30],"major":[7],"data":[8,34],"quality":[9,84],"concern":[10],"in":[11,99,141],"large":[12],"databases.":[13],"To":[14],"detect":[15],"duplicates,":[16],"entity":[17],"resolution":[18],"also":[19],"known":[20],"as":[21,29],"duplication":[22,72],"detection":[23,73],"or":[24],"record":[25],"linkage":[26],"used":[28,98],"part":[31],"the":[33,44,50,64,83,86,110],"cleaning":[35],"process":[36],"to":[37,43,81],"identify":[38],"that":[40,53,114,126,130],"potentially":[41],"refer":[42],"same":[45],"real-world":[46],"entity.":[47],"We":[48],"present":[49],"Stringer":[51,80],"system":[52],"provides":[54],"an":[55],"evaluation":[56,124],"framework":[57],"for":[58,135],"understanding":[59],"what":[60],"barriers":[61],"remain":[62],"towards":[63],"goal":[65],"truly":[67],"scalable":[68],"and":[69,146],"general":[70],"purpose":[71],"algorithms.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"use":[79],"evaluate":[82],"clusters":[87],"(groups":[88],"potential":[90],"duplicates)":[91],"obtained":[92],"from":[93],"several":[94],"unconstrained":[95],"clustering":[96,128],"algorithms":[97,119,129],"concert":[100],"with":[101],"approximate":[102,117],"join":[103,118],"techniques.":[104],"Our":[105,122],"work":[106],"motivated":[108],"by":[109],"recent":[111],"significant":[112],"advancements":[113],"have":[115,131],"made":[116],"highly":[120],"scalable.":[121],"extensive":[123],"reveals":[125],"some":[127],"never":[132],"been":[133],"considered":[134],"detection,":[137],"perform":[138],"extremely":[139],"well":[140],"terms":[142],"both":[144],"accuracy":[145],"scalability.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":29},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}