{"id":"https://openalex.org/W4392386152","doi":"https://doi.org/10.3389/fdata.2024.1296552","title":"A scalable MapReduce-based design of an unsupervised entity resolution system","display_name":"A scalable MapReduce-based design of an unsupervised entity resolution system","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4392386152","doi":"https://doi.org/10.3389/fdata.2024.1296552","pmid":"https://pubmed.ncbi.nlm.nih.gov/38495849"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2024.1296552","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1296552","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1296552/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1296552/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015340472","display_name":"Nicholas Kofi Akortia Hagan","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Kofi Akortia Hagan","raw_affiliation_strings":["Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080276323","display_name":"John R. Talburt","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John R. Talburt","raw_affiliation_strings":["Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102624573","display_name":"Kris E. Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kris E. Anderson","raw_affiliation_strings":["Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Sciences, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109687958","display_name":"Deasia Hagan","orcid":null},"institutions":[{"id":"https://openalex.org/I102401767","display_name":"University of Arkansas at Little Rock","ror":"https://ror.org/04fttyv97","country_code":"US","type":"education","lineage":["https://openalex.org/I102401767"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deasia Hagan","raw_affiliation_strings":["Department of Rhetoric and Writing, University of Arkansas at Little Rock, Little Rock, AR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Rhetoric and Writing, University of Arkansas at Little Rock, Little Rock, AR, United States","institution_ids":["https://openalex.org/I102401767"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015340472","https://openalex.org/A5080276323"],"corresponding_institution_ids":["https://openalex.org/I102401767"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":0.6935,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70137012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"7","issue":null,"first_page":"1296552","last_page":"1296552"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9865000247955322,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9661999940872192,"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":0.8832284212112427},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7160012722015381},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5250905752182007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.480160653591156},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4521895945072174},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4518605172634125},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4295029640197754},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41109517216682434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35029464960098267},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3416108191013336},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32033008337020874},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22836214303970337},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10689479112625122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8832284212112427},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7160012722015381},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5250905752182007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.480160653591156},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4521895945072174},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4518605172634125},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4295029640197754},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41109517216682434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35029464960098267},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3416108191013336},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32033008337020874},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22836214303970337},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10689479112625122}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2024.1296552","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1296552","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1296552/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmid:38495849","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38495849","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10941646","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10941646","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10941646/pdf/fdata-07-1296552.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:e6bbeb98293d435a8dd8cd7f1e4461d4","is_oa":true,"landing_page_url":"https://doaj.org/article/e6bbeb98293d435a8dd8cd7f1e4461d4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2024.1296552","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2024.1296552","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1296552/pdf","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G4156043112","display_name":"RII Track-1: Data Analytics that are Robust and Trusted (DART): From Smart Curation to Socially Aware Decision Making","funder_award_id":"1946391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392386152.pdf","grobid_xml":"https://content.openalex.org/works/W4392386152.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W146810917","https://openalex.org/W1545348482","https://openalex.org/W1827980970","https://openalex.org/W1981590391","https://openalex.org/W1985982729","https://openalex.org/W1986017822","https://openalex.org/W2031250218","https://openalex.org/W2135054486","https://openalex.org/W2173213060","https://openalex.org/W2523829097","https://openalex.org/W2535168187","https://openalex.org/W2748156246","https://openalex.org/W2827854627","https://openalex.org/W2925054201","https://openalex.org/W2934044474","https://openalex.org/W2980226560","https://openalex.org/W2997562227","https://openalex.org/W3014295153","https://openalex.org/W3027456727","https://openalex.org/W3112013808","https://openalex.org/W3119203516","https://openalex.org/W3176546289","https://openalex.org/W4230692091","https://openalex.org/W4285289706","https://openalex.org/W4312897655","https://openalex.org/W4361286889","https://openalex.org/W4388053097","https://openalex.org/W6605873061","https://openalex.org/W6638721794","https://openalex.org/W6667993270","https://openalex.org/W6857713182"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2610007503"],"abstract_inverted_index":{"Traditional":[0],"data":[1,10,24,53,74,83,118,137],"curation":[2,75],"processes":[3,25,29,45,76,105],"typically":[4],"depend":[5],"on":[6,220,258,292],"human":[7],"intervention.":[8],"As":[9],"volume":[11],"and":[12,30,177,208,218,247,252,317],"variety":[13],"grow":[14],"exponentially,":[15],"organizations":[16],"are":[17,173,210,244],"striving":[18],"to":[19,41,47,87,102,166,192,230,305],"increase":[20],"efficiency":[21],"of":[22,51,60,71,113,147,155,196,203,226,236,240,249,254,261,274,280,307],"their":[23],"by":[26,150,175,256],"automating":[27],"manual":[28],"making":[31],"them":[32],"as":[33,35,93],"unsupervised":[34,44,62,129,178],"possible.":[36],"An":[37],"additional":[38],"challenge":[39],"is":[40,68,106,125,183,229,284],"make":[42],"these":[43],"scalable":[46,212],"meet":[48],"the":[49,58,88,94,110,144,148,152,159,194,204,232,237,241,245,259,275,281],"demands":[50],"increased":[52],"volume.":[54,119],"This":[55,139],"paper":[56],"describes":[57],"parallelization":[59,153,161],"an":[61,126,189],"entity":[63],"resolution":[64],"(ER)":[65],"process.":[66],"ER":[67,104,114,130,289],"a":[69,214,271],"component":[70],"many":[72],"different":[73],"because":[77,109],"it":[78],"clusters":[79,133],"records":[80,217],"from":[81,135,294,303],"multiple":[82,311],"sources":[84],"that":[85,299],"refer":[86],"same":[89,95],"real-world":[90],"entity,":[91],"such":[92],"customer,":[96],"patient,":[97],"or":[98],"product.":[99],"The":[100,120,186,199,224,278],"ability":[101],"scale":[103],"particularly":[107],"important":[108],"computation":[111],"effort":[112],"increases":[115],"quadratically":[116],"with":[117,314],"Data":[121,267],"Washing":[122,268],"Machine":[123,269],"(DWM)":[124],"already":[127],"proposed":[128,160,282],"system":[131,283],"which":[132,243],"references":[134,309],"diverse":[136],"sources.":[138],"work":[140],"aims":[141],"at":[142],"solving":[143],"single-threaded":[145,201],"nature":[146,154],"DWM":[149,187,205,242],"adopting":[151],"Hadoop":[156,262,266],"MapReduce.":[157,263],"However,":[158],"method":[162],"can":[163,301],"be":[164],"applied":[165],"both":[167],"supervised":[168],"systems,":[169,179],"where":[170,180],"matching":[171],"rules":[172],"created":[174],"experts,":[176],"expert":[181],"intervention":[182],"not":[184,211],"required.":[185],"uses":[188],"entropy":[190],"measure":[191],"self-evaluate":[193],"quality":[195],"record":[197],"clustering.":[198],"current":[200,238],"implementations":[202],"in":[206],"Python":[207],"Java":[209],"beyond":[213],"few":[215],"1,000":[216],"rely":[219],"large,":[221],"shared":[222,250],"memory.":[223],"objective":[225],"this":[227],"research":[228],"solve":[231],"major":[233],"two":[234],"shortcomings":[235],"design":[239],"creation":[246],"usage":[248],"memory":[251],"lack":[253],"scalability":[255,279],"leveraging":[257],"power":[260],"We":[264],"propose":[265],"(HDWM),":[270],"MapReduce":[272],"implementation":[273],"legacy":[276],"DWM.":[277],"displayed":[285],"using":[286,310],"publicly":[287],"available":[288],"datasets.":[290],"Based":[291],"results":[293],"our":[295],"experiment,":[296],"we":[297],"conclude":[298],"HDWM":[300],"cluster":[302],"1,000's":[304],"millions":[306],"equivalent":[308],"computational":[312],"nodes":[313],"independent":[315],"RAM":[316],"CPU":[318],"cores.":[319]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}