{"id":"https://openalex.org/W1568607842","doi":"https://doi.org/10.1109/icde.2015.7113268","title":"Cleaning uncertain data with a noisy crowd","display_name":"Cleaning uncertain data with a noisy crowd","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1568607842","doi":"https://doi.org/10.1109/icde.2015.7113268","mag":"1568607842"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2015.7113268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","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/A5100374113","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-3306-9317"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Chen Jason Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China","Hong Kong Univ. of Science and Tech, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong Univ. of Science and Tech, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China","Hong Kong Univ. of Science and Tech, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong Univ. of Science and Tech, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051874566","display_name":"Yongxin Tong","orcid":"https://orcid.org/0000-0002-5598-0312"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongxin Tong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China","Hong Kong Univ. of Science and Tech, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong Univ. of Science and Tech, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China","Hong Kong Univ. of Science and Tech, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong Univ. of Science and Tech, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100374113"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":11.2855,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97975152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"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":1.0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9950000047683716,"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/T11182","display_name":"Auction Theory and Applications","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.9181545972824097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7732889652252197},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7034870386123657},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.6688272356987},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6342650651931763},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5102767944335938},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49037814140319824},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.48013707995414734},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.46437469124794006},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4616924524307251},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44073486328125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3842354714870453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29065045714378357}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9181545972824097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732889652252197},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7034870386123657},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.6688272356987},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6342650651931763},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5102767944335938},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49037814140319824},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.48013707995414734},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.46437469124794006},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4616924524307251},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44073486328125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3842354714870453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29065045714378357},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1109/icde.2015.7113268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-72856","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-72856","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1566959760","https://openalex.org/W1583345983","https://openalex.org/W1610496399","https://openalex.org/W1671823646","https://openalex.org/W1945952945","https://openalex.org/W1974554406","https://openalex.org/W1977331029","https://openalex.org/W1982856917","https://openalex.org/W1993685897","https://openalex.org/W2004443904","https://openalex.org/W2010780779","https://openalex.org/W2013922699","https://openalex.org/W2020740057","https://openalex.org/W2028818097","https://openalex.org/W2038822667","https://openalex.org/W2041361017","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2058179030","https://openalex.org/W2076357412","https://openalex.org/W2080379754","https://openalex.org/W2088422262","https://openalex.org/W2092819480","https://openalex.org/W2098365426","https://openalex.org/W2101620066","https://openalex.org/W2103269600","https://openalex.org/W2118370002","https://openalex.org/W2129444086","https://openalex.org/W2130578025","https://openalex.org/W2131565021","https://openalex.org/W2138642981","https://openalex.org/W2138781105","https://openalex.org/W2145492473","https://openalex.org/W2161126263","https://openalex.org/W2163051926","https://openalex.org/W2171472464","https://openalex.org/W2950833813","https://openalex.org/W2951864179","https://openalex.org/W3139506240","https://openalex.org/W4230939871","https://openalex.org/W6634966889","https://openalex.org/W6636177537","https://openalex.org/W6644904181","https://openalex.org/W6672615329","https://openalex.org/W6673642881","https://openalex.org/W6679424342","https://openalex.org/W6768433217"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114","https://openalex.org/W2094985717"],"abstract_inverted_index":{"Uncertain":[0],"data":[1,113,145],"has":[2,132],"been":[3],"emerged":[4],"as":[5],"an":[6,176,181],"important":[7],"problem":[8],"in":[9,166],"database":[10],"systems":[11],"due":[12],"to":[13,29,38,86,90,107,110,135,153],"the":[14,22,44,49,67,92,112,130,140,160,188,208],"imprecise":[15],"nature":[16],"of":[17,69,81,94,118,163],"many":[18],"applications.":[19],"To":[20,185],"handle":[21],"uncertainty,":[23],"probabilistic":[24],"databases":[25],"can":[26],"be":[27,60],"used":[28,199],"store":[30],"uncertain":[31,73,95,144],"data,":[32],"and":[33,180,194,203,218],"querying":[34],"facilities":[35],"are":[36,121,146,198],"provided":[37],"yield":[39],"answers":[40],"with":[41,101,115,210],"confidence.":[42],"However,":[43],"uncertainty":[45],"may":[46,58],"propagate,":[47],"hence":[48],"returned":[50],"results":[51],"from":[52,143],"a":[53,79,88,102,133,215,219],"query":[54],"or":[55],"mining":[56],"process":[57],"not":[59],"useful.":[61],"In":[62],"this":[63,125,167],"paper,":[64,168],"we":[65,76,105,169,190],"leverage":[66],"power":[68],"crowdsourcing":[70,221],"for":[71,124,158,200],"cleaning":[72],"data.":[74,96],"Specifically,":[75],"will":[77],"design":[78,108],"set":[80,162],"Human":[82],"Intelligence":[83],"Tasks":[84],"(HIT)s":[85],"ask":[87],"crowd":[89,131,217],"improve":[91,187],"quality":[93,114],"Each":[97],"HIT":[98],"is":[99],"associated":[100],"cost,":[103],"thus,":[104],"need":[106],"solutions":[109,209],"maximize":[111],"minimal":[116],"number":[117],"HITs.":[119,164],"There":[120],"two":[122,150],"obstacles":[123,151],"non-trivial":[126],"optimization":[127],"-":[128],"first,":[129],"probability":[134],"return":[136],"incorrect":[137],"answers;":[138],"second,":[139],"HITs":[141],"decomposed":[142],"often":[147],"correlated.":[148],"These":[149],"lead":[152],"very":[154],"high":[155],"computational":[156],"cost":[157],"selecting":[159],"optimal":[161],"Thus,":[165],"have":[170,206],"addressed":[171],"these":[172],"challenges":[173],"by":[174],"designing":[175],"effective":[177,201],"approximation":[178],"algorithm":[179],"efficient":[182],"heuristic":[183],"solution.":[184],"further":[186],"efficiency,":[189],"derive":[191],"tight":[192],"lower":[193],"upper":[195],"bounds,":[196],"which":[197],"filtering":[202],"estimation.":[204],"We":[205],"verified":[207],"extensive":[211],"experiments":[212],"on":[213],"both":[214],"simulated":[216],"real":[220],"platform.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}