{"id":"https://openalex.org/W4399668113","doi":"https://doi.org/10.1145/3661167.3661213","title":"Data Quality Assessment in the Wild: Findings from GitHub","display_name":"Data Quality Assessment in the Wild: Findings from GitHub","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399668113","doi":"https://doi.org/10.1145/3661167.3661213"},"language":"en","primary_location":{"id":"doi:10.1145/3661167.3661213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661213","pdf_url":null,"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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3661167.3661213","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099127823","display_name":"Ipek Ustunboyacioglu","orcid":"https://orcid.org/0009-0000-3084-6689"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ipek Ustunboyacioglu","raw_affiliation_strings":["Jheronimus Academy of Data Science, Tilburg University, Netherlands"],"affiliations":[{"raw_affiliation_string":"Jheronimus Academy of Data Science, Tilburg University, Netherlands","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061039582","display_name":"Indika Kumara","orcid":"https://orcid.org/0000-0003-4355-0494"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Indika Kumara","raw_affiliation_strings":["Jheronimus Academy of Data Science, Tilburg University, Netherlands"],"affiliations":[{"raw_affiliation_string":"Jheronimus Academy of Data Science, Tilburg University, Netherlands","institution_ids":["https://openalex.org/I193700539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072127726","display_name":"Dario Di Nucci","orcid":"https://orcid.org/0000-0002-3861-1902"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dario Di Nucci","raw_affiliation_strings":["Department of Computer Science, University of Salerno, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000349425","display_name":"Damian A. Tamburri","orcid":"https://orcid.org/0000-0003-1230-8961"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Damian Andrew Tamburri","raw_affiliation_strings":["Jheronimus Academy of Data Science, Eindhoven University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Jheronimus Academy of Data Science, Eindhoven University of Technology, Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049150712","display_name":"Willem\u2010Jan van den Heuvel","orcid":"https://orcid.org/0000-0003-2929-413X"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Willem-Jan Van Den Heuvel","raw_affiliation_strings":["Jheronimus Academy of Data Science, Tilburg University, Netherlands"],"affiliations":[{"raw_affiliation_string":"Jheronimus Academy of Data Science, Tilburg University, Netherlands","institution_ids":["https://openalex.org/I193700539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099127823"],"corresponding_institution_ids":["https://openalex.org/I193700539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09604891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9939000010490417,"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/T11937","display_name":"Research Data Management Practices","score":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.6635035276412964},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6143820285797119},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5053032040596008},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.16499322652816772},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09778076410293579},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.07661983370780945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635035276412964},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6143820285797119},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5053032040596008},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.16499322652816772},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09778076410293579},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.07661983370780945},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3661167.3661213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661213","pdf_url":null,"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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3661167.3661213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661213","pdf_url":null,"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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2110710386","https://openalex.org/W2117366235","https://openalex.org/W2487200295","https://openalex.org/W2544486974","https://openalex.org/W3035250811","https://openalex.org/W3135196179","https://openalex.org/W3160786003","https://openalex.org/W3205379156","https://openalex.org/W4229772528","https://openalex.org/W4280601623","https://openalex.org/W4285728233","https://openalex.org/W4312355141","https://openalex.org/W4382677674","https://openalex.org/W4385977054","https://openalex.org/W4389249692"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W1963988314","https://openalex.org/W1924500548"],"abstract_inverted_index":{"Data":[0],"quality":[1,17,33,47,80,87,135],"is":[2,49,96],"critical":[3],"to":[4,82,138],"make":[5],"data-driven":[6],"business":[7],"decisions":[8],"reliable,":[9],"accurate,":[10],"and":[11,26,35,63,84,106,116,149],"complete.":[12],"As":[13],"a":[14,21],"result,":[15],"data":[16,32,46,79,134],"assessment":[18],"has":[19],"become":[20],"prevalent":[22],"topic":[23],"among":[24],"researchers":[25],"practitioners.":[27],"Previous":[28],"studies":[29],"have":[30],"surveyed":[31],"tools":[34,48,62,81,136],"used":[36,61],"them":[37],"in":[38],"industrial":[39],"projects.":[40],"However,":[41,109],"the":[42,58,86,126,133,140,143],"practitioners\u2019":[43],"adoption":[44],"of":[45,88,132,142],"mainly":[50],"unexplored.":[51],"In":[52],"this":[53],"study,":[54],"we":[55],"systematically":[56],"selected":[57],"five":[59],"widely":[60],"analyzed":[64],"498":[65],"GitHub":[66],"repositories":[67,111],"that":[68,75],"use":[69,78,94,131],"those":[70],"tools.":[71],"Our":[72],"findings":[73],"show":[74],"practitioners":[76],"increasingly":[77],"assess":[83,139],"improve":[85],"their":[89],"data.":[90],"The":[91,118,129],"most":[92,110,127],"common":[93],"case":[95],"software":[97],"development":[98,119],"(49.2%),":[99],"followed":[100,145],"by":[101,146],"learning":[102],"(25.5%),":[103],"teaching":[104],"(9.2%),":[105],"research":[107],"(0.4%).":[108],"(69%)":[112],"showed":[113],"less":[114],"activities":[115],"collaboration.":[117],"projects,":[120],"especially":[121],"with":[122],"industry-based":[123],"owners,":[124],"were":[125],"active.":[128],"predominant":[130],"was":[137],"completeness":[141],"data,":[144],"uniqueness,":[147],"validity,":[148],"referential":[150],"integrity.":[151]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
