{"id":"https://openalex.org/W4391840379","doi":"https://doi.org/10.1145/3648476","title":"Cleenex: Support for User Involvement during an Iterative Data Cleaning Process","display_name":"Cleenex: Support for User Involvement during an Iterative Data Cleaning Process","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391840379","doi":"https://doi.org/10.1145/3648476"},"language":"en","primary_location":{"id":"doi:10.1145/3648476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3648476","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3648476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102007589","display_name":"Jo\u00e3o L. M. Pereira","orcid":"https://orcid.org/0000-0002-3247-5524"},"institutions":[{"id":"https://openalex.org/I21803372","display_name":"University of \u00c9vora","ror":"https://ror.org/02gyps716","country_code":"PT","type":"education","lineage":["https://openalex.org/I21803372"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Jo\u00e3o L. M. Pereira","raw_affiliation_strings":["VISTA Lab, Algoritmi Center, University of \u00c9vora, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-3247-5524","affiliations":[{"raw_affiliation_string":"VISTA Lab, Algoritmi Center, University of \u00c9vora, Portugal","institution_ids":["https://openalex.org/I21803372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017651127","display_name":"Manuel J. Fonseca","orcid":"https://orcid.org/0000-0002-3559-828X"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Manuel J. Fonseca","raw_affiliation_strings":["LASIGE, Faculdade de Ci\u00eancias, Universidade de Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-3559-828X","affiliations":[{"raw_affiliation_string":"LASIGE, Faculdade de Ci\u00eancias, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047829447","display_name":"Ant\u00f3nia Lopes","orcid":"https://orcid.org/0000-0003-0688-3521"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ant\u00f3nia Lopes","raw_affiliation_strings":["LASIGE, Faculdade de Ci\u00eancias, Universidade de Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-0688-3521","affiliations":[{"raw_affiliation_string":"LASIGE, Faculdade de Ci\u00eancias, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010625393","display_name":"H\u00e9l\u00e9na Galhardas","orcid":"https://orcid.org/0000-0002-9330-3910"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Helena Galhardas","raw_affiliation_strings":["INESC-ID and Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-9330-3910","affiliations":[{"raw_affiliation_string":"INESC-ID and Instituto Superior T\u00e9cnico, Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102007589"],"corresponding_institution_ids":["https://openalex.org/I21803372"],"apc_list":null,"apc_paid":null,"fwci":1.3451,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80602969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9861000180244446,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512410879135132},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6868643760681152},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6499271392822266},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6116531491279602},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.5005455017089844},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48290133476257324},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46572965383529663},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41895365715026855},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.1539430022239685},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10553780198097229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512410879135132},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6868643760681152},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6499271392822266},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6116531491279602},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.5005455017089844},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48290133476257324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46572965383529663},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41895365715026855},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.1539430022239685},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10553780198097229},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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":2,"locations":[{"id":"doi:10.1145/3648476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3648476","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:dspace.uevora.pt:10174/40223","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3648476","pdf_url":null,"source":{"id":"https://openalex.org/S4306401462","display_name":"Repositorio Universidade de \u00c9vora (Universidade de \u00c9vora)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I21803372","host_organization_name":"University of \u00c9vora","host_organization_lineage":["https://openalex.org/I21803372"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1145/3648476","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3648476","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3648476","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1759428316","display_name":"LASIGE - Extreme Computing","funder_award_id":"UIDP/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2089664753","display_name":"LASIGE - Extreme Computing","funder_award_id":"UIDB/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G2441341484","display_name":"Instituto de Engenharia de Sistemas e Computadores, Investiga\u00e7\u00e3o e Desenvolvimento em Lisboa","funder_award_id":"UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3604284585","display_name":null,"funder_award_id":"ref. UIDB/00408/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391840379.pdf","grobid_xml":"https://content.openalex.org/works/W4391840379.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W183249055","https://openalex.org/W1494137514","https://openalex.org/W1610496399","https://openalex.org/W1791587663","https://openalex.org/W2028222220","https://openalex.org/W2063103859","https://openalex.org/W2081186682","https://openalex.org/W2099637074","https://openalex.org/W2132490332","https://openalex.org/W2169940602","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2896587760","https://openalex.org/W2998531464","https://openalex.org/W3046491668","https://openalex.org/W3082197983","https://openalex.org/W3099255643","https://openalex.org/W3197847098","https://openalex.org/W4214671568","https://openalex.org/W4243565423","https://openalex.org/W4317767732","https://openalex.org/W4321448364","https://openalex.org/W6607508199","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W1789991335","https://openalex.org/W2748020237","https://openalex.org/W2135768893","https://openalex.org/W176219849","https://openalex.org/W3021414116"],"abstract_inverted_index":{"The":[0],"existence":[1],"of":[2,5,10,46,54,96,154,175,178,207],"large":[3],"amounts":[4],"data":[6,12,16,48,55,81,103,112,131,142,148,165,179,197,200,217],"increases":[7],"the":[8,44,52,70,109,155,160,191,205,229,238],"probability":[9],"occurring":[11],"quality":[13,49],"problems.":[14],"A":[15],"cleaning":[17,56,82,113,132,143,149,196,201,218],"process":[18],"that":[19,84,106,158,187],"corrects":[20],"these":[21],"problems":[22,50],"is":[23,79,210],"usually":[24],"an":[25,91,140,152],"iterative":[26,92,141],"process,":[27,93,144,202],"because":[28],"it":[29,236],"may":[30],"need":[31,224],"to":[32,37,43,58,66,98,122,237],"be":[33,67],"re-executed":[34],"and":[35,51,145,170,245],"refined":[36],"produce":[38],"high-quality":[39],"data.":[40,76,101],"Moreover,":[41,102,214],"due":[42],"specificity":[45],"some":[47],"limitation":[53],"programs":[57],"cover":[59],"all":[60],"problems,":[61],"often":[62],"a":[63,94,130,167,171,199],"user":[64,110,137,161,176,192],"has":[65],"involved":[68],"during":[69,139,198],"program":[71],"executions":[72],"by":[73],"manually":[74,163,195],"repairing":[75,164],"However,":[77],"there":[78],"no":[80],"framework":[83,133],"appropriately":[85],"supports":[86],"this":[87],"involvement":[88,138],"in":[89,111,173,212],"such":[90],"form":[95],"human-in-the-loop,":[97],"clean":[99],"structured":[100],"preparation":[104,180],"tools":[105,181,240],"somehow":[107],"involve":[108],"processes":[114],"have":[115],"not":[116],"been":[117],"evaluated":[118],"with":[119,134,166,182,220],"real":[120,183,222],"users":[121,223],"assess":[123],"their":[124],"effort.":[125],"Therefore,":[126],"we":[127],"propose":[128],"Cleenex,":[129,221],"support":[135,159],"for":[136,203,242],"conduct":[146],"two":[147],"experimental":[150],"evaluations:":[151],"assessment":[153],"Cleenex":[156,188],"components":[157,189],"when":[162,194,215],"simulated":[168],"user;":[169],"comparison,":[172,243],"terms":[174],"involvement,":[177],"users.":[184],"Results":[185],"show":[186],"reduce":[190],"effort":[193],"example,":[204],"number":[206],"tuples":[208],"visualized":[209],"reduced":[211],"99%.":[213],"performing":[216],"tasks":[219],"less":[225],"time/effort":[226],"(e.g.,":[227],"half":[228],"clicks)":[230],"and,":[231],"based":[232],"on":[233],"questionnaires,":[234],"prefer":[235],"other":[239],"used":[241],"OpenRefine":[244],"Pentaho":[246],"Data":[247],"Integration.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}
