{"id":"https://openalex.org/W4220819090","doi":"https://doi.org/10.1145/3522664.3528621","title":"Data smells in public datasets","display_name":"Data smells in public datasets","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W4220819090","doi":"https://doi.org/10.1145/3522664.3528621"},"language":"en","primary_location":{"id":"doi:10.1145/3522664.3528621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528621","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528621","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063990793","display_name":"Arumoy Shome","orcid":"https://orcid.org/0000-0002-3778-5150"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Arumoy Shome","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004310055","display_name":"Lu\u00eds Cruz","orcid":"https://orcid.org/0000-0002-1615-355X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lu\u00eds Cruz","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090401584","display_name":"Arie van Deursen","orcid":"https://orcid.org/0000-0003-4850-3312"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arie van Deursen","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063990793"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":6.6838,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96776301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9987999796867371,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9894999861717224,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-smell","display_name":"Code smell","score":0.7278320789337158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6809173822402954},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6179722547531128},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5909940600395203},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5188233256340027},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.32832393050193787},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.21055001020431519},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15333953499794006},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08382362127304077}],"concepts":[{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.7278320789337158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809173822402954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6179722547531128},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5909940600395203},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5188233256340027},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.32832393050193787},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.21055001020431519},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15333953499794006},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08382362127304077},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3522664.3528621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528621","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528621","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},{"id":"pmh:oai:arXiv.org:2203.08007","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.08007","pdf_url":"https://arxiv.org/pdf/2203.08007","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:tudelft.nl:uuid:88a2eb26-cc21-4213-88db-406dfcad8f3b","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:88a2eb26-cc21-4213-88db-406dfcad8f3b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3522664.3528621","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3522664.3528621","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3522664.3528621","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220819090.pdf","grobid_xml":"https://content.openalex.org/works/W4220819090.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1498291970","https://openalex.org/W1964401032","https://openalex.org/W2056797234","https://openalex.org/W2056952837","https://openalex.org/W2153887189","https://openalex.org/W2421097601","https://openalex.org/W2437617937","https://openalex.org/W2508117657","https://openalex.org/W2574666645","https://openalex.org/W2757656223","https://openalex.org/W2808642230","https://openalex.org/W2889249015","https://openalex.org/W2896671475","https://openalex.org/W2900961173","https://openalex.org/W2922234936","https://openalex.org/W2945759596","https://openalex.org/W2953617193","https://openalex.org/W3007157104","https://openalex.org/W3048650942","https://openalex.org/W3090668201","https://openalex.org/W3098910265","https://openalex.org/W3118813946","https://openalex.org/W3123920941","https://openalex.org/W3130255873","https://openalex.org/W3135371071","https://openalex.org/W3154383848","https://openalex.org/W3160786003","https://openalex.org/W3178161004","https://openalex.org/W3183307799"],"related_works":["https://openalex.org/W3134933787","https://openalex.org/W3116338676","https://openalex.org/W2786648929","https://openalex.org/W2774816643","https://openalex.org/W4248495898","https://openalex.org/W2137479650","https://openalex.org/W2245479382","https://openalex.org/W3139296374","https://openalex.org/W4387803644","https://openalex.org/W4210350690"],"abstract_inverted_index":{"The":[0],"adoption":[1],"of":[2,32,70,81,94],"Artificial":[3],"Intelligence":[4],"(AI)":[5],"in":[6,58,86,98],"high-stakes":[7],"domains":[8],"such":[9],"as":[10],"healthcare,":[11],"wildlife":[12],"preservation,":[13],"autonomous":[14],"driving":[15],"and":[16,36,105],"criminal":[17],"justice":[18],"system":[19],"calls":[20],"for":[21],"a":[22,67],"data-centric":[23],"approach":[24],"to":[25,42,62,77],"AI.":[26],"Data":[27],"scientists":[28],"spend":[29],"the":[30,38,53,92],"majority":[31],"their":[33],"time":[34],"studying":[35],"wrangling":[37],"data,":[39],"yet":[40],"tools":[41],"aid":[43],"them":[44],"with":[45],"data":[46,55,71,95,108],"analysis":[47],"are":[48],"lacking.":[49],"This":[50],"study":[51],"identifies":[52],"recurrent":[54],"quality":[56,96],"issues":[57,97],"public":[59,103],"datasets.":[60],"Analogous":[61],"code":[63],"smells,":[64],"we":[65,100],"introduce":[66],"novel":[68],"catalogue":[69],"smells":[72],"that":[73],"can":[74],"be":[75],"used":[76],"indicate":[78],"early":[79],"signs":[80],"problems":[82],"or":[83],"technical":[84],"debt":[85],"machine":[87],"learning":[88],"systems.":[89],"To":[90],"understand":[91],"prevalence":[93],"datasets,":[99],"analyse":[101],"25":[102],"datasets":[104],"identify":[106],"14":[107],"smells.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
