{"id":"https://openalex.org/W4408480012","doi":"https://doi.org/10.1145/3721985","title":"Unsupervised Evaluation of Entity Resolution","display_name":"Unsupervised Evaluation of Entity Resolution","publication_year":2025,"publication_date":"2025-03-15","ids":{"openalex":"https://openalex.org/W4408480012","doi":"https://doi.org/10.1145/3721985"},"language":"en","primary_location":{"id":"doi:10.1145/3721985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721985","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3721985","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067500298","display_name":"Charini Nanayakkara","orcid":"https://orcid.org/0000-0002-7603-1845"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Charini Nanayakkara","raw_affiliation_strings":["School of Computing, Australian National University","School of Computing, Australian National University, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7603-1845","affiliations":[{"raw_affiliation_string":"School of Computing, Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"School of Computing, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022945960","display_name":"Peter Christen","orcid":"https://orcid.org/0000-0003-3435-2015"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I1299119326","display_name":"Scottish Agricultural Science Agency","ror":"https://ror.org/006sw6d69","country_code":"GB","type":"government","lineage":["https://openalex.org/I1299119326"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Peter Christen","raw_affiliation_strings":["School of Computing, Australian National University","Scottish Centre for Administrative Data Research, University of Edinburgh","Scottish Centre for Administrative Data Research, University of Edinburgh, Edinburgh, United Kingdom of Great Britain and Northern Ireland","School of Computing, Australian National University, Canberra, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3435-2015","affiliations":[{"raw_affiliation_string":"School of Computing, Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Scottish Centre for Administrative Data Research, University of Edinburgh","institution_ids":["https://openalex.org/I1299119326"]},{"raw_affiliation_string":"Scottish Centre for Administrative Data Research, University of Edinburgh, Edinburgh, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Computing, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073205641","display_name":"Victor Christen","orcid":"https://orcid.org/0000-0001-7175-7359"},"institutions":[{"id":"https://openalex.org/I147765834","display_name":"Leipzig University of Applied Sciences","ror":"https://ror.org/03xgcq477","country_code":"DE","type":"education","lineage":["https://openalex.org/I147765834"]},{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Victor Christen","raw_affiliation_strings":["Computer Science, University Leipzig","Computer Science, University Leipzig, Leipzig, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7175-7359","affiliations":[{"raw_affiliation_string":"Computer Science, University Leipzig","institution_ids":["https://openalex.org/I147765834","https://openalex.org/I926574661"]},{"raw_affiliation_string":"Computer Science, University Leipzig, Leipzig, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.9163,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97067737,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9902999997138977,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9819999933242798,"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/computer-science","display_name":"Computer science","score":0.778389036655426},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5326516032218933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.379976749420166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3351874351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778389036655426},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5326516032218933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.379976749420166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3351874351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721985","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3721985","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721985","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4272082136","display_name":"University of Edinburgh 2022-2026 ADR UK Programme","funder_award_id":"ES/W010321/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1983345514","https://openalex.org/W1987971958","https://openalex.org/W1995099886","https://openalex.org/W1996851530","https://openalex.org/W2015997296","https://openalex.org/W2026499502","https://openalex.org/W2037587716","https://openalex.org/W2042913039","https://openalex.org/W2052390074","https://openalex.org/W2062225614","https://openalex.org/W2064244056","https://openalex.org/W2072240081","https://openalex.org/W2073471108","https://openalex.org/W2131681506","https://openalex.org/W2143896029","https://openalex.org/W2148019918","https://openalex.org/W2148524305","https://openalex.org/W2158703410","https://openalex.org/W2162630660","https://openalex.org/W2256424113","https://openalex.org/W2541780901","https://openalex.org/W2542998387","https://openalex.org/W2552528958","https://openalex.org/W2569876941","https://openalex.org/W2606460416","https://openalex.org/W2748156246","https://openalex.org/W2805602976","https://openalex.org/W2921759054","https://openalex.org/W2929962453","https://openalex.org/W2950211242","https://openalex.org/W2981519032","https://openalex.org/W2989757146","https://openalex.org/W2990998616","https://openalex.org/W3004300812","https://openalex.org/W3014295153","https://openalex.org/W3019395470","https://openalex.org/W3048871918","https://openalex.org/W3099768174","https://openalex.org/W3136501774","https://openalex.org/W3138971549","https://openalex.org/W3139815093","https://openalex.org/W4210754024","https://openalex.org/W4242744113","https://openalex.org/W4318613010","https://openalex.org/W4366290747","https://openalex.org/W4366729173","https://openalex.org/W4382397550","https://openalex.org/W4399252848","https://openalex.org/W6793965918"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Entity":[0,36],"resolution":[1,22,37,67,122,161,215],"is":[2,84],"the":[3,11,55,94,111,118,156,164,186,194,208],"problem":[4],"of":[5,20,47,71,96,120,158,166,174,188],"identifying":[6],"records":[7,48,72],"that":[8,74],"refer":[9],"to":[10,30,54,61,78,116,154,237],"same":[12,56],"entity":[13,21,66,83,121,160,214],"from":[14,24,225],"one":[15,79,87],"or":[16,58,135,140,207],"multiple":[17,152,222],"databases.":[18],"Applications":[19],"range":[23],"health":[25],"and":[26,33,81,99,110,176,193,233],"social":[27],"science":[28],"research":[29],"national":[31],"security":[32],"online":[34],"commerce.":[35],"can":[38,137,230],"be":[39,138],"viewed":[40],"as":[41,51,107,179,181],"a":[42],"classification":[43],"task":[44],"where":[45],"pairs":[46],"are":[49,101,113,131,198],"classified":[50],"matches":[52,98],"(referring":[53,60],"entity)":[57],"non-matches":[59,100],"different":[62],"entities).":[63],"Alternatively,":[64],"clustering-based":[65],"methods":[68,153,197,220],"generate":[69],"clusters":[70],"such":[73,106],"each":[75,82],"cluster":[76],"refers":[77],"entity,":[80],"represented":[85],"by":[86,170,212],"cluster.":[88],"If":[89],"ground":[90,128,167],"truth":[91,129,168],"data":[92,130,169,223],"in":[93],"form":[95],"known":[97],"available,":[102,134],"then":[103],"performance":[104],"measures":[105],"precision,":[108,191],"recall,":[109,192],"F-measure,":[112],"commonly":[114],"used":[115],"evaluate":[117,155],"quality":[119,143,157],"methods.":[123],"In":[124],"practical":[125],"applications,":[126],"however,":[127],"often":[132],"not":[133],"they":[136,229],"incomplete":[139],"biased,":[141],"making":[142],"evaluation":[144],"challenging.":[145],"To":[146],"overcome":[147],"this":[148],"gap,":[149],"we":[150],"develop":[151],"an":[159,213],"result":[162],"without":[163],"need":[165],"calculating":[171],"estimated":[172],"numbers":[173],"true":[175,239],"false":[177],"matches,":[178],"well":[180],"missed":[182],"matches.":[183],"These":[184],"allow":[185],"calculation":[187],"estimates":[189,235],"for":[190],"F-measure.":[195],"Our":[196],"either":[199],"based":[200],"on":[201,221],"analysing":[202],"links":[203],"(classified":[204],"record":[205],"pairs)":[206],"clustering":[209],"structure":[210],"provided":[211],"method.":[216],"We":[217],"validate":[218],"our":[219],"sets":[224],"diverse":[226],"domains,":[227],"showing":[228],"obtain":[231],"precision":[232],"recall":[234],"close":[236],"their":[238],"values.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}