{"id":"https://openalex.org/W2081118310","doi":"https://doi.org/10.1145/2723372.2723739","title":"Crowd-Based Deduplication","display_name":"Crowd-Based Deduplication","publication_year":2015,"publication_date":"2015-05-27","ids":{"openalex":"https://openalex.org/W2081118310","doi":"https://doi.org/10.1145/2723372.2723739","mag":"2081118310"},"language":"en","primary_location":{"id":"doi:10.1145/2723372.2723739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2723739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of 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/A5100736050","display_name":"Sibo Wang","orcid":"https://orcid.org/0000-0003-1892-6971"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Sibo Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore, SINGAPORE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore, SINGAPORE#TAB#","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010903591","display_name":"Xiaokui Xiao","orcid":"https://orcid.org/0000-0003-0914-4580"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaokui Xiao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore, SINGAPORE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore, SINGAPORE#TAB#","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048876270","display_name":"Chun-Hee Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chun-Hee Lee","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore","Nanyang Technological University, Singapore, SINGAPORE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore, SINGAPORE#TAB#","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100736050"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":18.2524,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.99223432,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1263","last_page":"1277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9984999895095825,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9972000122070312,"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":0.9968000054359436,"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/data-deduplication","display_name":"Data deduplication","score":0.9866235852241516},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.814895749092102},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.8035943508148193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7935462594032288},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6396037340164185},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6055364012718201},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4222777783870697},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3778659403324127},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.324495404958725},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3229389190673828},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.250683069229126},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19877830147743225},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05919066071510315}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9866235852241516},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.814895749092102},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8035943508148193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935462594032288},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6396037340164185},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6055364012718201},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4222777783870697},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3778659403324127},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.324495404958725},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3229389190673828},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.250683069229126},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19877830147743225},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05919066071510315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2723372.2723739","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723372.2723739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G6202558549","display_name":null,"funder_award_id":"M4080094.020","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G90434880","display_name":null,"funder_award_id":"ARC19/14","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W35043963","https://openalex.org/W1610496399","https://openalex.org/W1647671624","https://openalex.org/W1974554406","https://openalex.org/W1977810318","https://openalex.org/W1982119153","https://openalex.org/W1998475090","https://openalex.org/W2024770506","https://openalex.org/W2028818097","https://openalex.org/W2035274534","https://openalex.org/W2038281398","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2069396035","https://openalex.org/W2069897123","https://openalex.org/W2076357412","https://openalex.org/W2085099553","https://openalex.org/W2091858563","https://openalex.org/W2098865355","https://openalex.org/W2100061495","https://openalex.org/W2106675345","https://openalex.org/W2107966677","https://openalex.org/W2108991785","https://openalex.org/W2113878109","https://openalex.org/W2119320829","https://openalex.org/W2131565021","https://openalex.org/W2133236963","https://openalex.org/W2143654071","https://openalex.org/W2145492473","https://openalex.org/W2148524305","https://openalex.org/W2154785834","https://openalex.org/W2161126263","https://openalex.org/W2163051926","https://openalex.org/W2164455818","https://openalex.org/W2164625277","https://openalex.org/W2168144930","https://openalex.org/W2295256067","https://openalex.org/W2295665070","https://openalex.org/W2296044363","https://openalex.org/W2400013274","https://openalex.org/W4251369550","https://openalex.org/W4254788633","https://openalex.org/W4285719527","https://openalex.org/W6759150888","https://openalex.org/W6768433217","https://openalex.org/W6771752040"],"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":{"Data":[0],"deduplication":[1],"stands":[2],"as":[3],"a":[4],"building":[5],"block":[6],"for":[7],"data":[8,11],"integration":[9],"and":[10],"cleaning.":[12],"The":[13],"state-of-the-art":[14],"techniques":[15],"focus":[16],"on":[17,34],"how":[18],"to":[19,22],"exploit":[20],"crowdsourcing":[21],"improve":[23],"the":[24,35],"accuracy":[25],"of":[26],"deduplication.":[27],"However,":[28],"they":[29],"either":[30],"incur":[31],"significant":[32],"overheads":[33],"crowd":[36],"or":[37],"offer":[38],"inferior":[39],"accuracy.":[40]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":10}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}
