{"id":"https://openalex.org/W1571692007","doi":"https://doi.org/10.3233/ia-140061","title":"Towards data cleansing via planning","display_name":"Towards data cleansing via planning","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1571692007","doi":"https://doi.org/10.3233/ia-140061","mag":"1571692007"},"language":"en","primary_location":{"id":"doi:10.3233/ia-140061","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ia-140061","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale: The international journal of the AIxIA","raw_type":"journal-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/A5058377858","display_name":"Roberto Boselli","orcid":"https://orcid.org/0000-0002-4574-3137"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Roberto Boselli","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049259722","display_name":"Mirko Cesarini","orcid":"https://orcid.org/0000-0001-9601-0403"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirko Cesarini","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047827615","display_name":"Fabio Mercorio","orcid":"https://orcid.org/0000-0001-6864-2702"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Mercorio","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039716498","display_name":"Mario Mezzanzanica","orcid":"https://orcid.org/0000-0003-0399-2810"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Mezzanzanica","raw_affiliation_strings":["CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"CRISP Research Centre, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]},{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058377858"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":2.8407,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90234887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":"1","first_page":"57","last_page":"69"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9824000000953674,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9695000052452087,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.8419082164764404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360190153121948},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6536979079246521},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6082916259765625},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5806866884231567},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5767761468887329},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5674483776092529},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5662645101547241},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5638930201530457},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.44978439807891846},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.44504687190055847},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3309032917022705},{"id":"https://openalex.org/keywords/process-management","display_name":"Process management","score":0.3230798840522766},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3221941590309143},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.16695243120193481},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.11226868629455566},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.10785737633705139},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1009158194065094}],"concepts":[{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.8419082164764404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360190153121948},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6536979079246521},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6082916259765625},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5806866884231567},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5767761468887329},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5674483776092529},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5662645101547241},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5638930201530457},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.44978439807891846},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.44504687190055847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3309032917022705},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.3230798840522766},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3221941590309143},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.16695243120193481},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.11226868629455566},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.10785737633705139},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1009158194065094},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/ia-140061","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ia-140061","pdf_url":null,"source":{"id":"https://openalex.org/S207922018","display_name":"Intelligenza Artificiale","issn_l":"1724-8035","issn":["1724-8035","2211-0097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligenza Artificiale: The international journal of the AIxIA","raw_type":"journal-article"},{"id":"pmh:oai:boa.unimib.it:10281/52120.3","is_oa":false,"landing_page_url":"http://hdl.handle.net/10281/52120","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articolo su rivista"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W116030894","https://openalex.org/W117906119","https://openalex.org/W125598877","https://openalex.org/W151538500","https://openalex.org/W160574391","https://openalex.org/W622135080","https://openalex.org/W997400855","https://openalex.org/W1011425321","https://openalex.org/W1499805410","https://openalex.org/W1529693658","https://openalex.org/W1539265392","https://openalex.org/W1544828112","https://openalex.org/W1555519929","https://openalex.org/W1567491469","https://openalex.org/W1587682423","https://openalex.org/W1604958321","https://openalex.org/W1610496399","https://openalex.org/W1611041715","https://openalex.org/W1660264423","https://openalex.org/W1668408280","https://openalex.org/W1700279323","https://openalex.org/W1773658184","https://openalex.org/W1777359101","https://openalex.org/W1813492422","https://openalex.org/W1925737511","https://openalex.org/W1985096808","https://openalex.org/W2004291985","https://openalex.org/W2018320462","https://openalex.org/W2025315843","https://openalex.org/W2026324192","https://openalex.org/W2033626294","https://openalex.org/W2036616350","https://openalex.org/W2046298800","https://openalex.org/W2046769817","https://openalex.org/W2046977065","https://openalex.org/W2047745978","https://openalex.org/W2053209119","https://openalex.org/W2060646170","https://openalex.org/W2060939697","https://openalex.org/W2065753378","https://openalex.org/W2068376489","https://openalex.org/W2089206172","https://openalex.org/W2094344402","https://openalex.org/W2097083865","https://openalex.org/W2101512350","https://openalex.org/W2134592632","https://openalex.org/W2137594618","https://openalex.org/W2150983842","https://openalex.org/W2161163216","https://openalex.org/W2171999426","https://openalex.org/W2289289418","https://openalex.org/W2293763696","https://openalex.org/W2400958823","https://openalex.org/W2576958202"],"related_works":["https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W4255072332","https://openalex.org/W2028861106","https://openalex.org/W3126834064","https://openalex.org/W1754154538","https://openalex.org/W3169246587","https://openalex.org/W4253714063","https://openalex.org/W2984010599"],"abstract_inverted_index":{"Nowadays":[0],"Information":[1],"Systems":[2],"generate":[3],"a":[4,71,86,103,110,121,157,170,176],"lot":[5],"of":[6,12,58,68,78,89,105,152,159],"data":[7,24,36,53,69,93,137,165,181],"for":[8,28,37,54,124,134,163,195],"supporting":[9],"the":[10,20,44,56,66,76,79,90,150,188],"activities":[11],"firms,":[13],"organisations,":[14],"and":[15,40,117,140,190],"state":[16,33],"agencies.":[17],"While":[18],"on":[19,43,92],"one":[21],"hand":[22,46],"such":[23,52,85],"are":[25,114],"primarily":[26],"collected":[27],"realising":[29],"domain-specific":[30],"services":[31],"(e.g.,":[32],"agencies":[34],"use":[35],"managing":[38],"healthcare":[39],"retirement":[41],"contributions)":[42],"other":[45],"domain":[47],"analysts":[48],"aim":[49],"at":[50,97],"using":[51,131],"studying":[55],"dynamics":[57],"subjects'":[59],"behaviours":[60],"or":[61],"phenomena":[62],"over":[63],"time.":[64],"Thus,":[65],"quality":[67,94,138],"plays":[70],"key":[72],"role":[73],"in":[74],"ensuring":[75],"effectiveness":[77],"overall":[80],"knowledge":[81],"discovery":[82],"process.":[83],"In":[84],"context,":[87],"most":[88],"research":[91],"is":[95,128],"aimed":[96],"automatically":[98,141],"identifying":[99,142],"cleansing":[100,143,161],"activities,":[101],"namely":[102],"sequence":[104],"actions":[106,162],"able":[107],"to":[108],"cleanse":[109],"dirty":[111],"dataset,":[112],"which":[113],"often":[115],"developed":[116],"coded":[118],"manually":[119],"requiring":[120],"relevant":[122],"effort":[123],"domain-experts.":[125],"This":[126],"work":[127],"concerned":[129],"with":[130],"AI":[132],"Planning":[133],"both":[135,187],"modelling":[136],"requirements":[139],"activities.":[144],"To":[145],"this":[146],"end,":[147],"we":[148,174],"formalise":[149],"concept":[151],"cost-optimal":[153],"Universal":[154],"Cleanser":[155],"-":[156,168],"collection":[158],"best":[160],"each":[164],"inconsistency":[166],"identified":[167],"as":[169],"planning":[171],"problem,":[172],"then":[173],"present":[175],"motivating":[177],"government":[178],"application":[179],"where":[180],"have":[182],"been":[183],"cleansed":[184,191],"accordingly,":[185],"making":[186],"source":[189],"datasets":[192],"publicly":[193],"available":[194],"download.":[196]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}