{"id":"https://openalex.org/W2948579574","doi":"https://doi.org/10.1109/access.2019.2920667","title":"Applying Cluster Refinement to Improve Crowd-Based Data Duplicate Detection Approach","display_name":"Applying Cluster Refinement to Improve Crowd-Based Data Duplicate Detection Approach","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948579574","doi":"https://doi.org/10.1109/access.2019.2920667","mag":"2948579574"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2920667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730331.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730331.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084017739","display_name":"Charles Roland Haruna","orcid":"https://orcid.org/0000-0002-8545-2916"},"institutions":[{"id":"https://openalex.org/I133771110","display_name":"University of Cape Coast","ror":"https://ror.org/0492nfe34","country_code":"GH","type":"education","lineage":["https://openalex.org/I133771110"]}],"countries":["GH"],"is_corresponding":true,"raw_author_name":"Charles Roland Haruna","raw_affiliation_strings":["Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana","institution_ids":["https://openalex.org/I133771110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102008799","display_name":"Mengshu Hou","orcid":"https://orcid.org/0000-0002-5283-7318"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengshu Hou","raw_affiliation_strings":["Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102789488","display_name":"Rui Xi","orcid":"https://orcid.org/0000-0002-6400-9106"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xi","raw_affiliation_strings":["Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105989021","display_name":"Moses Jojo Eghan","orcid":"https://orcid.org/0000-0001-7389-6758"},"institutions":[{"id":"https://openalex.org/I133771110","display_name":"University of Cape Coast","ror":"https://ror.org/0492nfe34","country_code":"GH","type":"education","lineage":["https://openalex.org/I133771110"]}],"countries":["GH"],"is_corresponding":false,"raw_author_name":"Moses Jojo Eghan","raw_affiliation_strings":["Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana","institution_ids":["https://openalex.org/I133771110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037211171","display_name":"Michael Y. Kpiebaareh","orcid":"https://orcid.org/0000-0002-1637-3050"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Michael Y. Kpiebaareh","raw_affiliation_strings":["Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031708267","display_name":"Lawrence Tandoh","orcid":"https://orcid.org/0000-0002-9078-1079"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"lawrence Tandoh","raw_affiliation_strings":["Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041237707","display_name":"Barbie Eghan-Yartel","orcid":null},"institutions":[{"id":"https://openalex.org/I133771110","display_name":"University of Cape Coast","ror":"https://ror.org/0492nfe34","country_code":"GH","type":"education","lineage":["https://openalex.org/I133771110"]}],"countries":["GH"],"is_corresponding":false,"raw_author_name":"Barbie Eghan-Yartel","raw_affiliation_strings":["Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana","institution_ids":["https://openalex.org/I133771110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085162497","display_name":"Maame G. Asante-Mensah","orcid":"https://orcid.org/0000-0003-0400-2866"},"institutions":[{"id":"https://openalex.org/I133771110","display_name":"University of Cape Coast","ror":"https://ror.org/0492nfe34","country_code":"GH","type":"education","lineage":["https://openalex.org/I133771110"]}],"countries":["GH"],"is_corresponding":false,"raw_author_name":"Maame G. Asante-Mensah","raw_affiliation_strings":["Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, University of Cape Coast, Cape Coast, Ghana","institution_ids":["https://openalex.org/I133771110"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084017739"],"corresponding_institution_ids":["https://openalex.org/I133771110"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1445,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56287934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"7","issue":null,"first_page":"77426","last_page":"77435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9988999962806702,"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":0.9988999962806702,"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/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9900000095367432,"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/data-deduplication","display_name":"Data deduplication","score":0.9612529873847961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8399118185043335},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6950728893280029},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6690633296966553},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6495862007141113},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5384286642074585},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5256744027137756},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30268508195877075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21514081954956055}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9612529873847961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399118185043335},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6950728893280029},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6690633296966553},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6495862007141113},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5384286642074585},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5256744027137756},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30268508195877075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21514081954956055},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2920667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730331.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:192fa2919cd245a0b90f58195758281a","is_oa":true,"landing_page_url":"https://doaj.org/article/192fa2919cd245a0b90f58195758281a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 77426-77435 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2920667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2920667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08730331.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G138440666","display_name":null,"funder_award_id":"1472067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4811743277","display_name":null,"funder_award_id":"2018YFC","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5767895881","display_name":null,"funder_award_id":"2018YFC0831800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6402079364","display_name":null,"funder_award_id":"61472067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6902961575","display_name":null,"funder_award_id":"2018YFC0831800","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948579574.pdf","grobid_xml":"https://content.openalex.org/works/W2948579574.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W35043963","https://openalex.org/W1547612978","https://openalex.org/W1992419399","https://openalex.org/W2002767255","https://openalex.org/W2025301163","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2081118310","https://openalex.org/W2091858563","https://openalex.org/W2097776316","https://openalex.org/W2106675345","https://openalex.org/W2119320829","https://openalex.org/W2121516976","https://openalex.org/W2163051926","https://openalex.org/W2204093302","https://openalex.org/W2295256067","https://openalex.org/W2296044363","https://openalex.org/W2606926586","https://openalex.org/W2729840144","https://openalex.org/W2753434909","https://openalex.org/W2768680874","https://openalex.org/W2803263920","https://openalex.org/W2804318406","https://openalex.org/W2899476671","https://openalex.org/W2914959486","https://openalex.org/W3146259567","https://openalex.org/W6632844220"],"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":{"In":[0,96],"this":[1,97],"paper,":[2,98,115],"we":[3,54,102],"present":[4],"an":[5,18,72,80],"extension":[6],"on":[7],"a":[8,25,34],"hybrid-based":[9,111],"deduplication":[10,76,112,146],"technique":[11],"in":[12,82,84,99],"entity":[13],"reconciliation":[14],"(ER),":[15],"by":[16],"proposing":[17],"algorithm":[19],"that":[20],"builds":[21],"clusters":[22,43,52,151],"upon":[23],"receiving":[24],"pre-specified":[26],"K":[27],"number":[28],"of":[29,41,62,105,140],"clusters,":[30],"and":[31,65,74,88,117,122,137],"second":[32],"developing":[33],"crowd-based":[35],"procedure":[36],"for":[37],"refining":[38],"the":[39,42,46,51,58,63,92,100,128,150],"results":[40,121],"produced":[44],"after":[45],"clustering":[47],"generation":[48,68],"phases.":[49],"With":[50],"refined,":[53],"aim":[55],"to":[56,70,78,110,127,149],"minimize":[57],"cost":[59,136],"metric":[60],"\u039b'(R)":[61],"solitary":[64],"compound":[66],"cluster":[67],"algorithms,":[69],"achieve":[71],"improved":[73],"efficient":[75],"method,":[77],"have":[79],"increase":[81],"accuracy":[83,139],"identifying":[85],"duplicate":[86],"records,":[87],"finally,":[89],"further":[90],"reduce":[91],"crowdsourcing":[93],"overheads":[94],"incurred.":[95],"experiments,":[101],"made":[103],"use":[104],"three":[106],"datasets":[107],"commonly":[108],"known":[109],"such":[113],"as":[114,142,144],"product,":[116],"restaurant.":[118],"The":[119],"performance":[120],"evaluations":[123],"demonstrate":[124],"clear":[125],"superiority":[126],"methods":[129],"compared":[130],"with":[131],"our":[132],"work":[133],"offering":[134],"low-crowdsourcing":[135],"high":[138],"deduplication,":[141],"well":[143],"better":[145],"efficiency":[147],"due":[148],"being":[152],"refined.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
