{"id":"https://openalex.org/W4312355141","doi":"https://doi.org/10.1145/3522664.3528590","title":"Data smells","display_name":"Data smells","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W4312355141","doi":"https://doi.org/10.1145/3522664.3528590"},"language":"en","primary_location":{"id":"doi:10.1145/3522664.3528590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528590","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528590","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033698477","display_name":"Harald Foidl","orcid":"https://orcid.org/0000-0002-6283-0419"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Harald Foidl","raw_affiliation_strings":["University of Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055476405","display_name":"Michael Felderer","orcid":"https://orcid.org/0000-0003-3818-4442"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Felderer","raw_affiliation_strings":["University of Innsbruck, Austria"],"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004548330","display_name":"Rudolf Ramler","orcid":"https://orcid.org/0000-0001-9903-6107"},"institutions":[{"id":"https://openalex.org/I4210126338","display_name":"Software Competence Center Hagenberg (Austria)","ror":"https://ror.org/02ks3nr96","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210126338"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Rudolf Ramler","raw_affiliation_strings":["Hagenberg GmbH, Austria"],"affiliations":[{"raw_affiliation_string":"Hagenberg GmbH, Austria","institution_ids":["https://openalex.org/I4210126338"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033698477"],"corresponding_institution_ids":["https://openalex.org/I190249584"],"apc_list":null,"apc_paid":null,"fwci":5.7639,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96732594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9980999827384949,"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":0.9980999827384949,"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/T10260","display_name":"Software Engineering Research","score":0.9973999857902527,"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/T10734","display_name":"Information and Cyber Security","score":0.9907000064849854,"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/code-smell","display_name":"Code smell","score":0.9586156010627747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6692689657211304},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6041254997253418},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5823750495910645},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5328742861747742},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.477008581161499},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.4728774428367615},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4692414104938507},{"id":"https://openalex.org/keywords/technical-debt","display_name":"Technical debt","score":0.4399571716785431},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.36796045303344727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2502390742301941},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.2393677532672882},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18659532070159912}],"concepts":[{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.9586156010627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692689657211304},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6041254997253418},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5823750495910645},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5328742861747742},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.477008581161499},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.4728774428367615},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4692414104938507},{"id":"https://openalex.org/C159198006","wikidata":"https://www.wikidata.org/wiki/Q1532172","display_name":"Technical debt","level":4,"score":0.4399571716785431},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.36796045303344727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2502390742301941},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2393677532672882},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18659532070159912},{"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},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3522664.3528590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528590","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3522664.3528590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528590","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528590","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G2714809983","display_name":null,"funder_award_id":"865891","funder_id":"https://openalex.org/F4320323031","funder_display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft"},{"id":"https://openalex.org/G3981068856","display_name":null,"funder_award_id":"888127","funder_id":"https://openalex.org/F4320323031","funder_display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft"}],"funders":[{"id":"https://openalex.org/F4320318434","display_name":"Bundesministerium f\u00fcr Klimaschutz, Umwelt, Energie, Mobilit\u00e4t, Innovation und Technologie","ror":null},{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"},{"id":"https://openalex.org/F4320327593","display_name":"Bundesministerium f\u00fcr Digitalisierung und Wirtschaftsstandort","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312355141.pdf","grobid_xml":"https://content.openalex.org/works/W4312355141.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1502624642","https://openalex.org/W1933103375","https://openalex.org/W1975675278","https://openalex.org/W2092416205","https://openalex.org/W2334523061","https://openalex.org/W2341832822","https://openalex.org/W2416172964","https://openalex.org/W2535336098","https://openalex.org/W2544486974","https://openalex.org/W2594899909","https://openalex.org/W2735864825","https://openalex.org/W2808642230","https://openalex.org/W2883645417","https://openalex.org/W2889249015","https://openalex.org/W2905588001","https://openalex.org/W2968356825","https://openalex.org/W2968594320","https://openalex.org/W2976127369","https://openalex.org/W3004493192","https://openalex.org/W3014393908","https://openalex.org/W3030932193","https://openalex.org/W3126220825","https://openalex.org/W3144571334","https://openalex.org/W3160786003","https://openalex.org/W3163055914","https://openalex.org/W3209362664","https://openalex.org/W3212464620","https://openalex.org/W4210294742","https://openalex.org/W4246152626","https://openalex.org/W4252462871"],"related_works":["https://openalex.org/W2966568451","https://openalex.org/W3100183864","https://openalex.org/W3216079787","https://openalex.org/W4376606832","https://openalex.org/W4214834810","https://openalex.org/W2123249410","https://openalex.org/W3082463427","https://openalex.org/W2031267719","https://openalex.org/W2728463376","https://openalex.org/W2076012125"],"abstract_inverted_index":{"High":[0],"data":[1,11,30,90,113,136],"quality":[2,12,31],"is":[3,22,126],"fundamental":[4],"for":[5,19,134],"today's":[6],"AI-based":[7,63,105],"systems.":[8,106],"However,":[9],"although":[10],"has":[13],"been":[14],"an":[15,56,143],"object":[16],"of":[17,26,39,59,104,111,142],"research":[18,27],"decades,":[20],"there":[21],"a":[23,71,109],"clear":[24],"lack":[25],"on":[28,94,147],"potential":[29],"issues":[32,40,83],"(e.g.,":[33,65],"ambiguous,":[34],"extraneous":[35],"values).":[36],"These":[37],"kinds":[38],"are":[41],"latent":[42],"in":[43,62,76,101],"nature":[44],"and":[45,92,99,138],"thus":[46],"often":[47],"not":[48],"obvious.":[49],"Nevertheless,":[50],"they":[51],"can":[52],"be":[53],"associated":[54],"with":[55],"increased":[57],"risk":[58],"future":[60],"problems":[61],"systems":[64],"technical":[66],"debt,":[67],"data-induced":[68],"faults).":[69],"As":[70],"counterpart":[72],"to":[73,81],"code":[74],"smells":[75,91,114,137],"software":[77],"engineering,":[78],"we":[79],"refer":[80],"such":[82],"as":[84],"Data":[85],"Smells.":[86],"This":[87],"article":[88,130],"conceptualizes":[89],"elaborates":[93],"their":[95],"causes,":[96],"consequences,":[97],"detection,":[98],"use":[100],"the":[102,129,140],"context":[103],"In":[107],"addition,":[108],"catalogue":[110],"36":[112],"divided":[115],"into":[116],"three":[117],"categories":[118],"(i.e.,":[119],"Believability":[120],"Smells,":[121,123],"Understandability":[122],"Consistency":[124],"Smells)":[125],"presented.":[127],"Moreover,":[128],"outlines":[131],"tool":[132],"support":[133],"detecting":[135],"presents":[139],"result":[141],"initial":[144],"smell":[145],"detection":[146],"more":[148],"than":[149],"240":[150],"real-world":[151],"datasets.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2023-01-04T00:00:00"}
