{"id":"https://openalex.org/W4318185167","doi":"https://doi.org/10.1109/bigdata55660.2022.10020407","title":"Deduplicating Large Volumes of Data from Natural and Legal Entities in the Governmental Field","display_name":"Deduplicating Large Volumes of Data from Natural and Legal Entities in the Governmental Field","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318185167","doi":"https://doi.org/10.1109/bigdata55660.2022.10020407"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020407","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020407","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5050097104","display_name":"Marcos Carvalho","orcid":"https://orcid.org/0000-0001-6474-6467"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Marcos Carvalho","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024201468","display_name":"V\u00edtor Mangaravite","orcid":"https://orcid.org/0000-0001-9824-5484"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vitor Mangaravite","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039246628","display_name":"Lucas M. Ponce","orcid":"https://orcid.org/0000-0002-1480-0039"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas M. Ponce","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006462585","display_name":"Luis H. Cantelli","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luis Cantelli","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064969719","display_name":"Bruno Campoi","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Campoi","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077838041","display_name":"Gabriel H. Nunes","orcid":"https://orcid.org/0000-0002-7823-3061"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel Nunes","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077039961","display_name":"Bruno Barbosa Miranda de Paiva","orcid":"https://orcid.org/0000-0001-8378-3650"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Barbosa Miranda de Paiva","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045978751","display_name":"Alberto H. F. Laender","orcid":"https://orcid.org/0000-0001-5032-2233"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alberto H. F. Laender","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andre Goncalves","raw_affiliation_strings":["Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais (UFMG),Department of Computer Science,Belo Horizonte,Brazil,31270-901","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5050097104"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":0.2573,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4884842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"41","issue":null,"first_page":"2206","last_page":"2213"},"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5424104928970337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5129313468933105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08939734101295471}],"concepts":[{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5424104928970337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5129313468933105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08939734101295471},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020407","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020407","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2053062910","https://openalex.org/W2101114896","https://openalex.org/W2135490589","https://openalex.org/W2164456230","https://openalex.org/W2203389554","https://openalex.org/W2213201020","https://openalex.org/W2492590231","https://openalex.org/W2780813414","https://openalex.org/W2889795791","https://openalex.org/W2893303656","https://openalex.org/W2904542630","https://openalex.org/W2944916929","https://openalex.org/W2963136927","https://openalex.org/W2977942577","https://openalex.org/W3006151378","https://openalex.org/W3014295153","https://openalex.org/W3136873384","https://openalex.org/W4200218369","https://openalex.org/W4206022580","https://openalex.org/W4223610968","https://openalex.org/W4226232030","https://openalex.org/W6744048070","https://openalex.org/W6754576228","https://openalex.org/W6811144485","https://openalex.org/W6983064821"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Record":[0],"Deduplication":[1],"(RD)":[2],"aims":[3],"to":[4,70,156,158],"identify":[5],"instances":[6],"that":[7],"represent":[8],"the":[9,17,20,24,30,64,88,93],"same":[10],"real-world":[11],"entity":[12],"in":[13,35,63,87,149],"data":[14,36,55],"repositories.":[15],"In":[16,39,108],"government":[18],"environment,":[19],"RD":[21],"process":[22],"facilitates":[23],"identification":[25],"of":[26,32,61,66,68,85,90,92,98,102,114,123,139,144,161],"irregularities":[27],"and":[28,47,76,100,134],"reduces":[29],"consumption":[31],"computing":[33],"resources":[34],"integration":[37],"tasks.":[38],"this":[40],"context,":[41],"we":[42],"propose":[43],"a":[44,83,142],"scalable,":[45],"effective":[46],"efficient":[48,133],"platform,":[49],"called":[50],"DedupeGov,":[51],"for":[52,136],"integrating":[53],"large":[54,59,137],"repositories":[56],"(i.e.,":[57],"with":[58,96,125],"volumes":[60,138],"data,":[62,140],"order":[65],"millions":[67],"records)":[69],"unify":[71],"duplicate":[72,106],"entities":[73],"from":[74],"multiple":[75],"different":[77,159],"sources.":[78],"Our":[79],"experimental":[80],"results":[81],"indicate":[82],"21.8%":[84],"reduction":[86],"number":[89],"records":[91,124,148],"original":[94],"repository":[95,143],"99%":[97],"precision":[99],"95%":[101],"recall":[103],"when":[104],"identifying":[105],"records.":[107],"addition,":[109],"our":[110,129],"platform":[111],"was":[112],"capable":[113],"building":[115],"more":[116],"complete":[117],"records,":[118],"eliminating":[119],"at":[120],"least":[121],"32%":[122],"null":[126],"attributes.":[127],"Furthermore,":[128],"solution":[130],"is":[131],"very":[132],"scalable":[135],"deduplicating":[141],"almost":[145],"400":[146],"million":[147],"around":[150],"one":[151],"hour,":[152],"besides":[153],"being":[154],"easy":[155],"generalize":[157],"types":[160],"entity.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}