{"id":"https://openalex.org/W4411121786","doi":"https://doi.org/10.1145/3743144","title":"A Language to Model and Simulate Data Quality Issues in Process Mining","display_name":"A Language to Model and Simulate Data Quality Issues in Process Mining","publication_year":2025,"publication_date":"2025-06-07","ids":{"openalex":"https://openalex.org/W4411121786","doi":"https://doi.org/10.1145/3743144"},"language":"en","primary_location":{"id":"doi:10.1145/3743144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743144","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013970379","display_name":"Marco Comuzzi","orcid":"https://orcid.org/0000-0002-6944-4705"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Marco Comuzzi","raw_affiliation_strings":["Ulsan National Institute of Science and Technology, UNIST","Ulsan National Institute of Science and Technology, UNIST, Ulsan, Korea (the Republic of)"],"affiliations":[{"raw_affiliation_string":"Ulsan National Institute of Science and Technology, UNIST","institution_ids":["https://openalex.org/I48566637"]},{"raw_affiliation_string":"Ulsan National Institute of Science and Technology, UNIST, Ulsan, Korea (the Republic of)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061768757","display_name":"Jonghyeon Ko","orcid":"https://orcid.org/0000-0002-8322-8056"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jonghyeon Ko","raw_affiliation_strings":["Queensland University of Technology","Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078031491","display_name":"Fabrizio Maria Maggi","orcid":"https://orcid.org/0000-0002-9089-6896"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Maggi","raw_affiliation_strings":["Free University of Bozen-Bolzano","Free University of Bozen-Bolzano, Bolzano Italy"],"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano","institution_ids":["https://openalex.org/I171543936"]},{"raw_affiliation_string":"Free University of Bozen-Bolzano, Bolzano Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013970379"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17466511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.996399998664856,"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":0.8277087807655334},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.625210165977478},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5410488843917847},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4583948850631714},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4571229815483093},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40646135807037354},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34630894660949707},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3403954803943634},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22328725457191467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277087807655334},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.625210165977478},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5410488843917847},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4583948850631714},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4571229815483093},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40646135807037354},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34630894660949707},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3403954803943634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22328725457191467},{"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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.1145/3743144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743144","pdf_url":null,"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"}],"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/W1540257307","https://openalex.org/W2099753123","https://openalex.org/W2101238481","https://openalex.org/W2336423265","https://openalex.org/W2524961085","https://openalex.org/W2526226593","https://openalex.org/W2589086755","https://openalex.org/W2593039357","https://openalex.org/W2940451250","https://openalex.org/W2969864379","https://openalex.org/W3005655192","https://openalex.org/W4220775938","https://openalex.org/W4285187659","https://openalex.org/W4285242502","https://openalex.org/W4294837811","https://openalex.org/W4300042523","https://openalex.org/W4309566818","https://openalex.org/W4360980888","https://openalex.org/W4362584032","https://openalex.org/W4381735785","https://openalex.org/W4383105110","https://openalex.org/W4386091406","https://openalex.org/W4387868908","https://openalex.org/W4402101057","https://openalex.org/W4402928874","https://openalex.org/W7046403695"],"related_works":["https://openalex.org/W2384667405","https://openalex.org/W2373216116","https://openalex.org/W2137479650","https://openalex.org/W2245479382","https://openalex.org/W2135768893","https://openalex.org/W3139296374","https://openalex.org/W3021414116","https://openalex.org/W176219849","https://openalex.org/W4387803644","https://openalex.org/W4210350690"],"abstract_inverted_index":{"Real-life":[0],"business":[1],"process":[2,14,98],"event":[3,55,86,116,136,170,210],"logs":[4,137],"may":[5,142],"suffer":[6],"from":[7],"significant":[8],"data":[9,88,100,118],"quality":[10,31,57,89,101,119],"problems":[11,58],"negatively":[12],"influencing":[13],"mining":[15,99],"analysis.":[16],"Over":[17],"time,":[18],"a":[19,46,64,81,175,203],"range":[20,204],"of":[21,34,45,54,97,128,135,152,167,205],"approaches":[22,36],"has":[23,182],"been":[24,60,183],"developed":[25],"to":[26,38,42,109,124,188,198],"detect":[27],"and":[28,52,69,112,132,154,192,201],"repair":[29],"these":[30,35],"problems.":[32],"Validation":[33],"tends":[37],"be":[39,107,143,196],"challenging":[40],"due":[41],"the":[43,50,95,126,148,165],"lack":[44],"ground":[47],"truth.":[48],"Moreover,":[49],"identification":[51],"definition":[53],"log":[56,87,117,171],"have":[59],"tackled":[61],"mainly":[62],"through":[63,138],"pattern-based":[65],"approach,":[66],"with":[67],"systematic":[68],"extensible":[70],"methods":[71],"currently":[72],"lacking.":[73],"In":[74],"this":[75],"article,":[76],"we":[77],"present":[78,147],"FLAWD":[79,105,153,181],",":[80],"formal":[82],"language":[83],"for":[84,130,164],"describing":[85],"issues":[90],"that":[91,162],"enables":[92],"solutions":[93],"addressing":[94],"shortcomings":[96],"research":[102,187],"identified":[103],"above.":[104],"can":[106,195],"used":[108,184,197],"formally":[110,199],"describe":[111,200],"possibly":[113],"reason":[114],"over":[115],"errors,":[120],"as":[121,123],"well":[122],"guide":[125],"development":[127],"tools":[129],"controlled":[131],"sophisticated":[133],"\u201cpolluting\u201d":[134],"which":[139],"benchmark":[140,190],"datasets":[141,191],"systematically":[144],"created.":[145],"We":[146,178],"abstract":[149],"syntax":[150],"grammar":[151],"an":[155],"open-source":[156],"software":[157],"tool":[158],"based":[159],"on":[160],"it":[161,194],"allows":[163],"insertion":[166],"all":[168],"so-called":[169],"imperfection":[172],"patterns":[173],"in":[174,185,208],"stochastic":[176],"manner.":[177],"show":[179],"how":[180,193],"our":[186],"generate":[189],"replicate":[202],"errors":[206],"found":[207],"real-life":[209],"logs.":[211]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
