{"id":"https://openalex.org/W4200001896","doi":"https://doi.org/10.3233/faia210316","title":"Data-Centric Machine Learning: Improving Model Performance and Understanding Through Dataset Analysis","display_name":"Data-Centric Machine Learning: Improving Model Performance and Understanding Through Dataset Analysis","publication_year":2021,"publication_date":"2021-12-02","ids":{"openalex":"https://openalex.org/W4200001896","doi":"https://doi.org/10.3233/faia210316"},"language":"en","primary_location":{"id":"doi:10.3233/faia210316","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia210316","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA210316","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA210316","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035416729","display_name":"Hannes Westermann","orcid":"https://orcid.org/0000-0002-4527-7316"},"institutions":[{"id":"https://openalex.org/I4210099985","display_name":"Research Unit on Children's Psychosocial Maladjustment","ror":"https://ror.org/00xd2zr10","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210099985"]},{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Hannes Westermann","raw_affiliation_strings":["Cyberjustice Laboratory, Facult\u00e9 de droit, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"Cyberjustice Laboratory, Facult\u00e9 de droit, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210099985","https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077762937","display_name":"Jarom\u00edr \u0160avelka","orcid":"https://orcid.org/0000-0002-3674-5456"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jarom\u00edr \u0160avelka","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108747973","display_name":"Vern R. Walker","orcid":null},"institutions":[{"id":"https://openalex.org/I139290212","display_name":"Hofstra University","ror":"https://ror.org/03pm18j10","country_code":"US","type":"education","lineage":["https://openalex.org/I139290212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vern R. Walker","raw_affiliation_strings":["LLT Lab, Maurice A. Deane School of Law, Hofstra University"],"affiliations":[{"raw_affiliation_string":"LLT Lab, Maurice A. Deane School of Law, Hofstra University","institution_ids":["https://openalex.org/I139290212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664770","display_name":"Kevin D. Ashley","orcid":"https://orcid.org/0000-0002-5535-0759"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin D. Ashley","raw_affiliation_strings":["School of Computing and Information, University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032948369","display_name":"Karim Benyekhlef","orcid":"https://orcid.org/0000-0001-9390-556X"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]},{"id":"https://openalex.org/I4210099985","display_name":"Research Unit on Children's Psychosocial Maladjustment","ror":"https://ror.org/00xd2zr10","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210099985"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Karim Benyekhlef","raw_affiliation_strings":["Cyberjustice Laboratory, Facult\u00e9 de droit, Universit\u00e9 de Montr\u00e9al"],"affiliations":[{"raw_affiliation_string":"Cyberjustice Laboratory, Facult\u00e9 de droit, Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I4210099985","https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035416729"],"corresponding_institution_ids":["https://openalex.org/I4210099985","https://openalex.org/I70931966"],"apc_list":null,"apc_paid":null,"fwci":2.4081,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91152396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9692000150680542,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9692000150680542,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9241999983787537,"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/computer-science","display_name":"Computer science","score":0.7683078050613403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6955616474151611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6808230876922607},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6000086665153503},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5978575944900513},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5309053659439087},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.525530993938446},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5175265669822693},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4791618883609772},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4715157747268677},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46849116683006287},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4553350806236267},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44043612480163574},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42723917961120605},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4134572744369507},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11827069520950317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06921693682670593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683078050613403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6955616474151611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808230876922607},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6000086665153503},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5978575944900513},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5309053659439087},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.525530993938446},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5175265669822693},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4791618883609772},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4715157747268677},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46849116683006287},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4553350806236267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44043612480163574},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42723917961120605},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4134572744369507},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11827069520950317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06921693682670593},{"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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:10.3233/faia210316","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia210316","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA210316","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia210316","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia210316","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA210316","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200001896.pdf","grobid_xml":"https://content.openalex.org/works/W4200001896.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2794557536","https://openalex.org/W2953830946","https://openalex.org/W2963656255","https://openalex.org/W2964051087","https://openalex.org/W2986692942","https://openalex.org/W3108142956","https://openalex.org/W3116474736","https://openalex.org/W3146670357","https://openalex.org/W4226160860","https://openalex.org/W4287252712","https://openalex.org/W4297824675","https://openalex.org/W6749879876","https://openalex.org/W6891982818"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W4317548404","https://openalex.org/W3022007134","https://openalex.org/W2130553454","https://openalex.org/W2021633306","https://openalex.org/W2087783760","https://openalex.org/W2006801911","https://openalex.org/W4308757581"],"abstract_inverted_index":{"Machine":[0],"learning":[1,89],"research":[2],"typically":[3],"starts":[4],"with":[5],"a":[6,22,47,55,86],"fixed":[7],"data":[8,48,61,97],"set":[9,49,98],"created":[10],"early":[11],"in":[12,29,34,46,107],"the":[13,18,30,51,64,74,78,83,109,120],"process.":[14],"The":[15],"focus":[16],"of":[17,36,54,85,111,119],"experiments":[19,92],"is":[20],"finding":[21],"model":[23],"and":[24,77,114],"training":[25],"procedure":[26],"that":[27,94],"result":[28],"best":[31],"possible":[32],"performance":[33,53,84,101],"terms":[35],"some":[37],"selected":[38],"evaluation":[39],"metric.":[40],"This":[41],"paper":[42],"explores":[43],"how":[44,69,96],"changes":[45,70],"influence":[50],"measured":[52],"model.":[56],"Using":[57],"three":[58],"publicly":[59],"available":[60],"sets":[62],"from":[63],"legal":[65],"domain,":[66],"we":[67],"investigate":[68],"to":[71,116],"their":[72],"size,":[73],"train/test":[75],"splits,":[76],"human":[79],"labelling":[80],"accuracy":[81],"impact":[82],"trained":[87,112],"deep":[88],"classifier.":[90],"Our":[91],"suggest":[93],"analyzing":[95],"properties":[99],"affect":[100],"can":[102],"be":[103],"an":[104],"important":[105],"step":[106],"improving":[108],"results":[110],"classifiers,":[113],"leads":[115],"better":[117],"understanding":[118],"obtained":[121],"results.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}