{"id":"https://openalex.org/W4406458491","doi":"https://doi.org/10.1109/bigdata62323.2024.10825531","title":"Evaluating Blocking Biases in Entity Matching","display_name":"Evaluating Blocking Biases in Entity Matching","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458491","doi":"https://doi.org/10.1109/bigdata62323.2024.10825531"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/A5115904524","display_name":"Mohmmad Hossein Moslemi","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mohmmad Hossein Moslemi","raw_affiliation_strings":["The University of Western Ontario,London,Canada"],"affiliations":[{"raw_affiliation_string":"The University of Western Ontario,London,Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114415541","display_name":"Harini Balamurugan","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Harini Balamurugan","raw_affiliation_strings":["The University of Western Ontario,London,Canada"],"affiliations":[{"raw_affiliation_string":"The University of Western Ontario,London,Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072207353","display_name":"Mostafa Milani","orcid":"https://orcid.org/0000-0002-3386-7079"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mostafa Milani","raw_affiliation_strings":["The University of Western Ontario,London,Canada"],"affiliations":[{"raw_affiliation_string":"The University of Western Ontario,London,Canada","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115904524"],"corresponding_institution_ids":["https://openalex.org/I125749732"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32090839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"73"},"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":0.9934999942779541,"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/T10028","display_name":"Topic Modeling","score":0.9846000075340271,"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/blocking","display_name":"Blocking (statistics)","score":0.8329085111618042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7116037607192993},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6012993454933167},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15345361828804016},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10871419310569763},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10094371438026428}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.8329085111618042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116037607192993},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6012993454933167},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15345361828804016},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10871419310569763},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10094371438026428}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1597164057","https://openalex.org/W1724849505","https://openalex.org/W1985558865","https://openalex.org/W1992930793","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2042458413","https://openalex.org/W2073471108","https://openalex.org/W2088008685","https://openalex.org/W2100960835","https://openalex.org/W2104511295","https://openalex.org/W2161600801","https://openalex.org/W2210065635","https://openalex.org/W2399361902","https://openalex.org/W2546672044","https://openalex.org/W2798649495","https://openalex.org/W2808963673","https://openalex.org/W2905135414","https://openalex.org/W2962781182","https://openalex.org/W2992897306","https://openalex.org/W3011807731","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3032015135","https://openalex.org/W3034997167","https://openalex.org/W3045854241","https://openalex.org/W3099734810","https://openalex.org/W3123375411","https://openalex.org/W3137039868","https://openalex.org/W3197468999","https://openalex.org/W3209119957","https://openalex.org/W4281721601","https://openalex.org/W4289258088","https://openalex.org/W4318187137","https://openalex.org/W4319975816","https://openalex.org/W4383051975","https://openalex.org/W4386125399","https://openalex.org/W4399252848","https://openalex.org/W4400910536","https://openalex.org/W6632038546","https://openalex.org/W6641058599","https://openalex.org/W6728551298","https://openalex.org/W6788477411"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2353762239","https://openalex.org/W66314852","https://openalex.org/W2185938410","https://openalex.org/W2484966135"],"abstract_inverted_index":{"Entity":[0],"Matching":[1],"(EM)":[2],"is":[3],"crucial":[4],"for":[5,75],"identifying":[6],"equivalent":[7],"data":[8,120],"entities":[9],"across":[10],"different":[11],"sources,":[12],"a":[13,36,73],"task":[14],"that":[15],"becomes":[16],"increasingly":[17],"challenging":[18],"with":[19],"the":[20,30,49,86,103,112],"growth":[21],"and":[22,88],"heterogeneity":[23],"of":[24,33,51,90,105],"data.":[25],"Blocking":[26],"techniques,":[27],"which":[28],"reduce":[29],"computational":[31],"complexity":[32],"EM,":[34,109],"play":[35],"vital":[37],"role":[38],"in":[39,46,78,108,111,119],"making":[40],"this":[41],"process":[42],"scalable.":[43],"Despite":[44],"advancements":[45],"blocking":[47,53,67,79,92,113],"methods,":[48,93],"issue":[50],"fairness\u2014where":[52],"may":[54],"inadvertently":[55],"favor":[56],"certain":[57],"demographic":[58],"groups\u2014has":[59],"been":[60],"largely":[61],"overlooked.":[62],"This":[63],"study":[64],"extends":[65],"traditional":[66],"metrics":[68],"to":[69,115],"incorporate":[70],"fairness,":[71],"providing":[72],"framework":[74],"assessing":[76],"bias":[77],"techniques.":[80],"Through":[81],"experimental":[82],"analysis,":[83],"we":[84],"evaluate":[85],"effectiveness":[87],"fairness":[89,107],"various":[91],"offering":[94],"insights":[95],"into":[96],"their":[97],"potential":[98],"biases.":[99],"Our":[100],"findings":[101],"highlight":[102],"importance":[104],"considering":[106],"particularly":[110],"phase,":[114],"ensure":[116],"equitable":[117],"outcomes":[118],"integration":[121],"tasks.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}