{"id":"https://openalex.org/W2907754081","doi":"https://doi.org/10.1109/icsai.2018.8599375","title":"Cost-Based and Effective Human-Machine Based Data Deduplication Model in Entity Reconciliation","display_name":"Cost-Based and Effective Human-Machine Based Data Deduplication Model in Entity Reconciliation","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2907754081","doi":"https://doi.org/10.1109/icsai.2018.8599375","mag":"2907754081"},"language":"en","primary_location":{"id":"doi:10.1109/icsai.2018.8599375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2018.8599375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Systems and Informatics (ICSAI)","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/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":false,"raw_author_name":"Charles R. Haruna","raw_affiliation_strings":["University of Cape Coast, Cape Coast, Ghana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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 J. Eghan","raw_affiliation_strings":["University of Cape Coast, Cape Coast, Ghana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Cape Coast, Cape Coast, Ghana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Cape Coast, Cape Coast, Ghana"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cape Coast, Cape Coast, Ghana","institution_ids":["https://openalex.org/I133771110"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1265","last_page":"1270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-deduplication","display_name":"Data deduplication","score":0.9804981350898743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8628868460655212},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7902805805206299},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.737341582775116},{"id":"https://openalex.org/keywords/crowds","display_name":"Crowds","score":0.6378486752510071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5935356616973877},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5703301429748535},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.531640887260437},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37573379278182983},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3577044606208801},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07512718439102173},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06732672452926636}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9804981350898743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8628868460655212},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7902805805206299},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.737341582775116},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.6378486752510071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5935356616973877},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5703301429748535},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.531640887260437},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37573379278182983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3577044606208801},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07512718439102173},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06732672452926636},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsai.2018.8599375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsai.2018.8599375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 5th International Conference on Systems and Informatics (ICSAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1547612978","https://openalex.org/W1981590391","https://openalex.org/W1992419399","https://openalex.org/W1998475090","https://openalex.org/W2012668444","https://openalex.org/W2028818097","https://openalex.org/W2053653724","https://openalex.org/W2055515830","https://openalex.org/W2056748234","https://openalex.org/W2065259291","https://openalex.org/W2081118310","https://openalex.org/W2097776316","https://openalex.org/W2106675345","https://openalex.org/W2119320829","https://openalex.org/W2121516976","https://openalex.org/W2145492473","https://openalex.org/W2148524305","https://openalex.org/W2163051926","https://openalex.org/W2204093302","https://openalex.org/W2400013274","https://openalex.org/W2750977903","https://openalex.org/W2899476671","https://openalex.org/W3146259567","https://openalex.org/W6650214927","https://openalex.org/W6712587460","https://openalex.org/W6768433217"],"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":[0,72],"real":[1],"world,":[2],"databases":[3],"often":[4],"have":[5,15],"several":[6],"records":[7],"representing":[8],"the":[9,43,51,87,91],"same":[10],"entity":[11],"and":[12,24,67,109,120,133],"these":[13],"duplicates":[14],"no":[16],"common":[17],"key,":[18],"thus":[19],"making":[20],"deduplication":[21,132,135],"difficult.":[22],"Machine-based":[23],"crowdsourcing":[25,140],"techniques":[26,119],"were":[27,37,46,63,83,93],"disjointly":[28],"used":[29,38,85,95],"in":[30,33,65],"improving":[31],"quality":[32],"data":[34,88],"deduplication.":[35],"Crowdsourcing":[36],"for":[39],"solving":[40],"tasks":[41],"that":[42],"machine-based":[44],"algorithms":[45],"not":[47],"good":[48,134],"at.":[49],"Though,":[50],"crowds,":[52],"compared":[53,115],"with":[54,116],"machines,":[55],"provided":[56],"relatively":[57],"more":[58],"accurate":[59],"results,":[60],"both":[61],"platforms":[62],"slow":[64],"execution":[66],"hence":[68],"expensive":[69],"to":[70,96],"implement.":[71],"this":[73],"paper,":[74,107],"a":[75,128],"hybrid":[76],"human-machine":[77],"system":[78],"was":[79,114],"proposed":[80],"where":[81],"machines":[82],"firstly":[84],"on":[86],"set":[89],"before":[90],"humans":[92],"further":[94],"identify":[97],"potential":[98],"duplicates.":[99],"We":[100],"performed":[101],"experiments":[102],"using":[103],"three":[104],"benchmark":[105],"datasets;":[106],"restaurant":[108],"product":[110],"datasets.":[111],"Our":[112],"algorithm":[113],"some":[117,124],"existing":[118],"our":[121],"approach":[122],"outperformed":[123],"methods":[125],"by":[126],"achieving":[127],"high":[129],"accuracy":[130],"of":[131],"efficiency":[136],"while":[137],"incurring":[138],"low":[139],"costs.":[141]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}