{"id":"https://openalex.org/W4205343531","doi":"https://doi.org/10.1109/bigdata52589.2021.9672002","title":"BUBBLE : A Quality-Aware Human-in-the-loop Entity Matching Framework","display_name":"BUBBLE : A Quality-Aware Human-in-the-loop Entity Matching Framework","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205343531","doi":"https://doi.org/10.1109/bigdata52589.2021.9672002"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9672002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672002","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044833699","display_name":"Naofumi Osawa","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naofumi Osawa","raw_affiliation_strings":["University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053260657","display_name":"Hiroyoshi Ito","orcid":"https://orcid.org/0000-0002-3265-7029"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyoshi Ito","raw_affiliation_strings":["University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037917400","display_name":"Yukihiro Fukushima","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukihiro Fukushima","raw_affiliation_strings":["Keio University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072661393","display_name":"Takashi Harada","orcid":"https://orcid.org/0000-0002-3739-2541"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Harada","raw_affiliation_strings":["Doshisha University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071533497","display_name":"Atsuyuki Morishima","orcid":"https://orcid.org/0000-0003-4606-9065"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuyuki Morishima","raw_affiliation_strings":["University of Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.26275062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3557","last_page":"3565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9742000102996826,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774002552032471},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.691889226436615},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6851104497909546},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.5867922306060791},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5794178247451782},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5519933104515076},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4919683635234833},{"id":"https://openalex.org/keywords/3-dimensional-matching","display_name":"3-dimensional matching","score":0.4811081290245056},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.46176427602767944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4535461664199829},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.45114845037460327},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4486088454723358},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.41928404569625854},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4181559681892395},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41337376832962036},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3683353662490845},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25488513708114624},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.17733511328697205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12242576479911804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774002552032471},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.691889226436615},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6851104497909546},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.5867922306060791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5794178247451782},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5519933104515076},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4919683635234833},{"id":"https://openalex.org/C72545166","wikidata":"https://www.wikidata.org/wiki/Q10866593","display_name":"3-dimensional matching","level":4,"score":0.4811081290245056},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.46176427602767944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4535461664199829},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.45114845037460327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4486088454723358},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.41928404569625854},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4181559681892395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41337376832962036},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3683353662490845},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25488513708114624},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.17733511328697205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12242576479911804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9672002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9672002","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W1610496399","https://openalex.org/W1647671624","https://openalex.org/W2024770506","https://openalex.org/W2042458413","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2104511295","https://openalex.org/W2107966677","https://openalex.org/W2117974736","https://openalex.org/W2138621090","https://openalex.org/W2163051926","https://openalex.org/W2171450492","https://openalex.org/W2171590421","https://openalex.org/W2542998387","https://openalex.org/W2612526608","https://openalex.org/W2612732335","https://openalex.org/W2612925715","https://openalex.org/W2750620035","https://openalex.org/W2903158431","https://openalex.org/W3092962901","https://openalex.org/W3151257466","https://openalex.org/W6601696544","https://openalex.org/W6636177537","https://openalex.org/W6636915900","https://openalex.org/W6684306766","https://openalex.org/W6756615331","https://openalex.org/W6784244503"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W4205343531"],"abstract_inverted_index":{"Entity":[0],"matching":[1,30,49,67,77,87,112,141],"is":[2,22,81,183],"an":[3],"issue":[4],"of":[5,16,54,166,170],"interest":[6],"in":[7,117],"information":[8],"integration":[9],"and":[10,31,72,122],"data":[11,140],"cleaning.":[12],"Since":[13],"the":[14,17,28,47,52,86,110,118,131,144,167,187],"representations":[15],"same":[18,168],"entity":[19,29,39,48,66,76],"vary,":[20],"it":[21],"often":[23],"impossible":[24],"to":[25,36,42,83,108,129,137,157,164,173],"fully":[26],"automate":[27],"require":[32],"human":[33,44,55],"inputs.":[34],"However,":[35],"guarantee":[37,75],"high-quality":[38],"matching,":[40],"how":[41],"integrate":[43],"resources":[45],"into":[46],"while":[50],"minimizing":[51],"cost":[53],"resources?":[56],"In":[57],"this":[58,100],"paper,":[59],"we":[60,93,104,123],"propose":[61],"BUBBLE,":[62],"a":[63,125,138],"novel":[64],"human-in-the-loop":[65],"framework":[68],"hybridizing":[69],"Bayesian":[70,79,96],"inference":[71,80],"crowdsourcing.":[73,89],"To":[74],"quality,":[78],"conducted":[82],"determine":[84],"whether":[85],"requires":[88],"We":[90,134],"show":[91,151],"that":[92,152,179],"can":[94,154],"define":[95],"error":[97],"rate":[98],"for":[99],"problem.":[101],"For":[102],"optimization,":[103],"use":[105],"metric":[106],"learning":[107],"select":[109],"candidate":[111],"pairs":[113],"by":[114],"nearest-neighbor":[115],"search":[116],"learned":[119],"embedding":[120],"space,":[121],"construct":[124],"k-nearest":[126],"neighbor":[127],"graph":[128],"avoid":[130],"redundant":[132],"matching.":[133],"applied":[135],"BUBBLE":[136,153],"bibliographic":[139],"problem":[142],"on":[143],"National":[145],"Diet":[146],"Library.":[147],"The":[148,175],"experimental":[149],"results":[150,162],"assign":[155],"tasks":[156],"humans":[158],"with":[159],"higher":[160],"quality":[161],"compared":[163],"those":[165],"number":[169],"task":[171],"assignments":[172],"humans.":[174],"result":[176],"also":[177],"shows":[178],"our":[180],"optimization":[181],"scheme":[182],"effective":[184],"without":[185],"sacrificing":[186],"quality.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}