{"id":"https://openalex.org/W1999294550","doi":"https://doi.org/10.1145/2666539.2666568","title":"Using clustering and transitivity to reduce the costs of crowdsourced entity resolution","display_name":"Using clustering and transitivity to reduce the costs of crowdsourced entity resolution","publication_year":2014,"publication_date":"2014-11-07","ids":{"openalex":"https://openalex.org/W1999294550","doi":"https://doi.org/10.1145/2666539.2666568","mag":"1999294550"},"language":"en","primary_location":{"id":"doi:10.1145/2666539.2666568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666539.2666568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Crowd-based Software Development Methods and Technologies","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/A5111237556","display_name":"Lisha Guo","orcid":"https://orcid.org/0009-0009-0886-3007"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisha Guo","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087952294","display_name":"Hailong Sun","orcid":"https://orcid.org/0000-0001-7654-5574"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Sun","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073478843","display_name":"Xudong Liu","orcid":"https://orcid.org/0000-0001-9803-7298"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Liu","raw_affiliation_strings":["Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9973000288009644,"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":0.8222290277481079},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7895492315292358},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.7803555130958557},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7510999441146851},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6130392551422119},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5542579293251038},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5431981682777405},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5278558731079102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4811021685600281},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4363982677459717},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4317493736743927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4196644425392151},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3846486806869507},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10636639595031738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222290277481079},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7895492315292358},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.7803555130958557},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7510999441146851},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6130392551422119},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5542579293251038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5431981682777405},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5278558731079102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4811021685600281},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4363982677459717},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4317493736743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196644425392151},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3846486806869507},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10636639595031738},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2666539.2666568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666539.2666568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Crowd-based Software Development Methods and Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W1570528139","https://openalex.org/W2020740057","https://openalex.org/W2025721839","https://openalex.org/W2041439319","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2065398649","https://openalex.org/W2105268242","https://openalex.org/W2111625757","https://openalex.org/W2145492473","https://openalex.org/W2163051926","https://openalex.org/W2164456230","https://openalex.org/W2168144930","https://openalex.org/W2181558882","https://openalex.org/W4299828299"],"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/W3207526114"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"is":[2,15,77],"the":[3,7,11,91,123,135,163,168,181,196],"process":[4],"of":[5,58,93,107,125,154,192],"identifying":[6],"data":[8,159],"records":[9,118,165],"representing":[10],"same":[12,169],"entity.":[13,170],"ER":[14,32,66],"a":[16,87,147],"highly":[17],"important":[18],"problem":[19],"in":[20,54,190],"software":[21],"and":[22,100,157,180,195],"application":[23],"domains.":[24],"For":[25],"example,":[26],"detecting":[27],"duplicate":[28],"bug":[29],"reports":[30],"with":[31,73,98,104,138,151,176],"can":[33,42],"greatly":[34],"save":[35],"developing":[36],"efforts.":[37],"In":[38,56,82,129],"most":[39],"cases,":[40],"humans":[41],"perform":[43],"better":[44],"than":[45],"computer":[46,74],"algorithms":[47],"due":[48],"to":[49,67,79,89,96,116,161,167],"complex":[50],"semantic":[51],"analysis":[52],"involved":[53],"ER.":[55],"light":[57],"this,":[59],"crowdsourcing":[60,76],"has":[61],"been":[62],"successfully":[63],"incorporated":[64],"into":[65,119],"improve":[68],"its":[69],"accuracy.":[70],"However,":[71],"compared":[72],"methods,":[75],"subject":[78],"higher":[80],"costs.":[81],"this":[83,130],"work,":[84],"we":[85,111,132,145,172],"propose":[86],"method":[88,185],"reduce":[90],"number":[92],"questions":[94,156],"asked":[95],"people":[97],"clustering":[99],"transitivity":[101,160],"analysis.":[102],"Firstly,":[103],"appropriate":[105],"choosing":[106],"two":[108,177],"similarity":[109,127],"thresholds,":[110],"use":[112],"unsupervised":[113],"machine":[114],"learning":[115],"cluster":[117,148],"multiple":[120],"clusters":[121],"on":[122],"basis":[124],"certain":[126],"metrics.":[128],"way,":[131],"prune":[133],"away":[134],"record":[136],"pairs":[137],"no":[139],"need":[140],"for":[141],"asking":[142],"people.":[143],"Secondly,":[144],"design":[146],"merging":[149],"algorithm":[150],"efficient":[152],"selection":[153],"crowdsourced":[155],"leveraging":[158],"detect":[162],"across-cluster":[164],"corresponding":[166],"Finally,":[171],"conduct":[173],"extensive":[174],"experiments":[175],"real-world":[178],"datasets":[179],"results":[182],"show":[183],"our":[184],"significantly":[186],"outperform":[187],"existing":[188],"methods":[189],"terms":[191],"incurred":[193],"costs":[194],"F1":[197],"metric.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}