{"id":"https://openalex.org/W3105059154","doi":"https://doi.org/10.4018/ijoci.2021010104","title":"An Automatic Blocking Keys Selection For Efficient Record Linkage","display_name":"An Automatic Blocking Keys Selection For Efficient Record Linkage","publication_year":2020,"publication_date":"2020-11-16","ids":{"openalex":"https://openalex.org/W3105059154","doi":"https://doi.org/10.4018/ijoci.2021010104","mag":"3105059154"},"language":"en","primary_location":{"id":"doi:10.4018/ijoci.2021010104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijoci.2021010104","pdf_url":null,"source":{"id":"https://openalex.org/S199269040","display_name":"International Journal of Organizational and Collective Intelligence","issn_l":"1947-9344","issn":["1947-9344","1947-9352"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Organizational and Collective Intelligence","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/A5112583413","display_name":"Hamid Naceur Benkhlaed","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125514","display_name":"Universit\u00e9 Djilali de Sidi Bel Abb\u00e8s","ror":"https://ror.org/0378szg41","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Hamid Naceur Benkhlaed","raw_affiliation_strings":["EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria"],"raw_orcid":"https://orcid.org/0000-0001-7354-4920","affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria","institution_ids":["https://openalex.org/I4210125514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055779460","display_name":"Djamal Berrabah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125514","display_name":"Universit\u00e9 Djilali de Sidi Bel Abb\u00e8s","ror":"https://ror.org/0378szg41","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Djamal Berrabah","raw_affiliation_strings":["EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria","institution_ids":["https://openalex.org/I4210125514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063189101","display_name":"Nassima Dif","orcid":"https://orcid.org/0000-0002-8683-3163"},"institutions":[{"id":"https://openalex.org/I4210125514","display_name":"Universit\u00e9 Djilali de Sidi Bel Abb\u00e8s","ror":"https://ror.org/0378szg41","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Nassima Dif","raw_affiliation_strings":["EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria"],"raw_orcid":"https://orcid.org/0000-0002-8683-3163","affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Djillali Liabes, Sidi Bel Abbes, Algeria","institution_ids":["https://openalex.org/I4210125514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023463946","display_name":"Faouzi Boufar\u00e8s","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091279","display_name":"Universit\u00e9 Sorbonne Paris Nord","ror":"https://ror.org/0199hds37","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210091279"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Faouzi Boufares","raw_affiliation_strings":["LIPN Laboratory, Paris 13 University, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIPN Laboratory, Paris 13 University, France","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I4210091279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19140859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":"1","first_page":"53","last_page":"70"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9302999973297119,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9107999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293237686157227},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7936077117919922},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7192320823669434},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6289145350456238},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6054259538650513},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.569367527961731},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5226756930351257},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5219780206680298},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5091299414634705},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5073794722557068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4780193567276001},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46783626079559326},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4474147856235504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3786601424217224},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11987027525901794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08254393935203552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293237686157227},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7936077117919922},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7192320823669434},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6289145350456238},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6054259538650513},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.569367527961731},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5226756930351257},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5219780206680298},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5091299414634705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5073794722557068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4780193567276001},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46783626079559326},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4474147856235504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3786601424217224},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11987027525901794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08254393935203552},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4018/ijoci.2021010104","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijoci.2021010104","pdf_url":null,"source":{"id":"https://openalex.org/S199269040","display_name":"International Journal of Organizational and Collective Intelligence","issn_l":"1947-9344","issn":["1947-9344","1947-9352"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Organizational and Collective Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2117366235","https://openalex.org/W2149454242","https://openalex.org/W2167101736","https://openalex.org/W2169171650","https://openalex.org/W2170039925","https://openalex.org/W2318295100","https://openalex.org/W2525762567","https://openalex.org/W2772334662","https://openalex.org/W2783385843","https://openalex.org/W2791895608","https://openalex.org/W2921419981","https://openalex.org/W2925054201","https://openalex.org/W2954876896","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W2099811626"],"abstract_inverted_index":{"One":[0],"of":[1,23,53,63,154],"the":[2,6,21,29,43,50,54,58,73,76,81,87,123,134,152,155,158,167,171],"important":[3],"processes":[4],"in":[5,33,75,94,166],"data":[7,59,88],"quality":[8],"field":[9],"is":[10,20,46,69,89,116,120,136],"record":[11],"linkage":[12],"(RL).":[13],"RL":[14,44],"(also":[15],"known":[16],"as":[17,138],"entity":[18,32],"resolution)":[19],"process":[22,45,55],"detecting":[24],"duplicates":[25],"that":[26,66],"refer":[27],"to":[28,85],"same":[30,77],"real-world":[31,149],"one":[34],"or":[35],"more":[36],"datasets.":[37],"The":[38,143],"most":[39,95],"critical":[40],"step":[41],"during":[42],"blocking,":[47],"which":[48],"reduces":[49],"quadratic":[51],"complexity":[52],"by":[56,99],"dividing":[57],"into":[60],"a":[61,90,100,106,139],"set":[62],"blocks.":[64],"By":[65],"way,":[67],"matching":[68],"done":[70,98],"only":[71],"between":[72],"records":[74],"block.":[78],"However,":[79],"selecting":[80],"best":[82,172],"blocking":[83,113,173],"keys":[84],"divide":[86],"hard":[91],"task,":[92],"and":[93,169],"cases,":[96],"it's":[97],"domain":[101],"expert.":[102],"In":[103],"this":[104],"paper,":[105],"novel":[107],"unsupervised":[108],"approach":[109,119],"for":[110,160],"an":[111],"automatic":[112],"key":[114],"selection":[115,141,162],"proposed.":[117],"This":[118],"based":[121],"on":[122,148],"recently":[124],"proposed":[125],"meta-heuristic":[126],"bald":[127],"eagles":[128],"search":[129],"(bes)":[130],"optimization":[131],"algorithm,":[132],"where":[133,157],"problem":[135],"treated":[137],"feature":[140,161],"case.":[142],"obtained":[144],"results":[145],"from":[146],"experiments":[147],"datasets":[150],"showed":[151],"efficiency":[153],"proposition":[156],"BES":[159],"outperformed":[163],"existed":[164],"approaches":[165],"literature":[168],"returned":[170],"keys.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
