{"id":"https://openalex.org/W3198597167","doi":"https://doi.org/10.1145/3472163.3472195","title":"Customized Eager-Lazy Data Cleansing for Satisfactory Big Data Veracity","display_name":"Customized Eager-Lazy Data Cleansing for Satisfactory Big Data Veracity","publication_year":2021,"publication_date":"2021-07-14","ids":{"openalex":"https://openalex.org/W3198597167","doi":"https://doi.org/10.1145/3472163.3472195","mag":"3198597167"},"language":"en","primary_location":{"id":"doi:10.1145/3472163.3472195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472163.3472195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th International Database Engineering &amp; Applications Symposium","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/A5039032451","display_name":"Soror Sahri","orcid":"https://orcid.org/0000-0002-1554-7565"},"institutions":[{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]},{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Soror Sahri","raw_affiliation_strings":["Universite Rene Descartes (Paris V), France"],"affiliations":[{"raw_affiliation_string":"Universite Rene Descartes (Paris V), France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006789671","display_name":"Rim Moussa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rim Moussa","raw_affiliation_strings":["Universite de 7 Novembre a Carthage, Tunisia"],"affiliations":[{"raw_affiliation_string":"Universite de 7 Novembre a Carthage, Tunisia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039032451"],"corresponding_institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241"],"apc_list":null,"apc_paid":null,"fwci":0.1743,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54368416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"24","issue":null,"first_page":"157","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8349364399909973},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7737575769424438},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6362259387969971},{"id":"https://openalex.org/keywords/trips-architecture","display_name":"TRIPS architecture","score":0.5592698454856873},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5563355684280396},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.5320186614990234},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4782737195491791},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.45898258686065674},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.453108012676239},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42901092767715454},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36105120182037354},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.08241885900497437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349364399909973},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7737575769424438},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6362259387969971},{"id":"https://openalex.org/C157085824","wikidata":"https://www.wikidata.org/wiki/Q2384809","display_name":"TRIPS architecture","level":2,"score":0.5592698454856873},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5563355684280396},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.5320186614990234},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4782737195491791},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.45898258686065674},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.453108012676239},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42901092767715454},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36105120182037354},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.08241885900497437},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472163.3472195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472163.3472195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th International Database Engineering &amp; Applications Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1567491469","https://openalex.org/W2046769817","https://openalex.org/W2056638635","https://openalex.org/W2137479650","https://openalex.org/W2176027998","https://openalex.org/W2316007180","https://openalex.org/W2604341722"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W2270762093","https://openalex.org/W3126834064","https://openalex.org/W4200551113","https://openalex.org/W2028861106","https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4255072332","https://openalex.org/W4210350690","https://openalex.org/W1754154538"],"abstract_inverted_index":{"Big":[0],"data":[1,8],"systems":[2],"are":[3,26],"becoming":[4],"mainstream":[5],"for":[6,11,71],"big":[7],"management":[9],"either":[10],"batch":[12],"processing":[13],"or":[14],"real-time":[15],"processing.":[16],"In":[17,39],"order":[18,66],"to":[19,29,77],"extract":[20],"insights":[21],"from":[22],"data,":[23],"quality":[24,48,52,59],"issues":[25,60],"very":[27],"important":[28],"address,":[30],"particularly.":[31],"A":[32],"veracity":[33,75],"assessment":[34],"model":[35,45],"is":[36],"consequently":[37],"needed.":[38],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44,63],"which":[46],"ties":[47],"of":[49,53],"datasets":[50],"and":[51,73],"query":[54],"resultsets.":[55],"We":[56,80],"particularly":[57],"examine":[58],"raised":[61],"by":[62],"given":[64],"dataset,":[65],"attributes":[67],"along":[68],"their":[69],"fitness":[70],"use":[72],"correlate":[74],"metrics":[76],"business":[78],"queries.":[79],"validate":[81],"our":[82],"work":[83],"using":[84],"the":[85],"open":[86],"dataset":[87],"NYC":[88],"taxi\u2019":[89],"trips.":[90]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
