{"id":"https://openalex.org/W4382024737","doi":"https://doi.org/10.1145/3603709","title":"A Data-centric AI Framework for Automating Exploratory Data Analysis and Data Quality Tasks","display_name":"A Data-centric AI Framework for Automating Exploratory Data Analysis and Data Quality Tasks","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382024737","doi":"https://doi.org/10.1145/3603709"},"language":"en","primary_location":{"id":"doi:10.1145/3603709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603709","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3603709","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102917997","display_name":"Hima Patel","orcid":"https://orcid.org/0000-0002-0031-8428"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hima Patel","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":"https://orcid.org/0000-0002-0031-8428","affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082881366","display_name":"Shanmukha Guttula","orcid":"https://orcid.org/0009-0001-1982-024X"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shanmukha Guttula","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":"https://orcid.org/0009-0001-1982-024X","affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054069765","display_name":"Nitin Gupta","orcid":"https://orcid.org/0000-0003-0177-6292"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nitin Gupta","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":"https://orcid.org/0000-0003-0177-6292","affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039554087","display_name":"Sandeep Hans","orcid":"https://orcid.org/0000-0003-4986-0688"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Hans","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":"https://orcid.org/0000-0003-4986-0688","affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046316553","display_name":"Ruhi Sharma Mittal","orcid":"https://orcid.org/0009-0002-2649-6844"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ruhi Sharma Mittal","raw_affiliation_strings":["IBM Research, India"],"raw_orcid":"https://orcid.org/0009-0002-2649-6844","affiliations":[{"raw_affiliation_string":"IBM Research, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102837113","display_name":"N. Lokesh","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lokesh N","raw_affiliation_strings":["IIT Bombay, India"],"raw_orcid":"https://orcid.org/0000-0002-1322-7218","affiliations":[{"raw_affiliation_string":"IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1243,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94855211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"15","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9976000189781189,"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":0.9976000189781189,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13398","display_name":"Data Analysis with R","score":0.9919999837875366,"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":0.8614330291748047},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6261163949966431},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.6085420250892639},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.527397096157074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.478158563375473},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45564186573028564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4049529433250427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3838081955909729},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.09942388534545898},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08743453025817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614330291748047},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6261163949966431},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.6085420250892639},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.527397096157074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.478158563375473},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45564186573028564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4049529433250427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3838081955909729},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.09942388534545898},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08743453025817871},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603709","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3603709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603709","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603709","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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382024737.pdf","grobid_xml":"https://content.openalex.org/works/W4382024737.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1666942233","https://openalex.org/W1983479840","https://openalex.org/W2001496424","https://openalex.org/W2002722920","https://openalex.org/W2029830529","https://openalex.org/W2031648200","https://openalex.org/W2051317694","https://openalex.org/W2054141820","https://openalex.org/W2064186732","https://openalex.org/W2096863518","https://openalex.org/W2146130798","https://openalex.org/W2287926972","https://openalex.org/W2414312413","https://openalex.org/W2480680997","https://openalex.org/W2767280887","https://openalex.org/W2783908707","https://openalex.org/W2889249015","https://openalex.org/W2901288224","https://openalex.org/W2904577797","https://openalex.org/W2949244208","https://openalex.org/W2955121492","https://openalex.org/W2997919412","https://openalex.org/W3003365835","https://openalex.org/W3035623224","https://openalex.org/W3109072952","https://openalex.org/W3127996554","https://openalex.org/W3156669901","https://openalex.org/W4241491750","https://openalex.org/W4248989888","https://openalex.org/W4293582904","https://openalex.org/W4300187280","https://openalex.org/W4313492028","https://openalex.org/W4385281412","https://openalex.org/W6772013027","https://openalex.org/W6823027048"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W4287027380","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W2135768893","https://openalex.org/W176219849","https://openalex.org/W3021414116"],"abstract_inverted_index":{"Democratisation":[0],"of":[1,119,141,215,217],"machine":[2,29],"learning":[3,30],"(ML)":[4],"has":[5],"been":[6],"an":[7,213],"important":[8],"theme":[9],"in":[10,38,184,197],"the":[11,15,24,59,66,100,117,134,139,154,159,163,176,192,208,225],"research":[12],"community":[13,26],"for":[14,65,89,96],"last":[16],"several":[17],"years":[18],"with":[19,27,111,148,207],"notable":[20],"progress":[21],"made":[22],"by":[23,62],"model-building":[25],"automated":[28],"models.":[31],"However,":[32],"data":[33,63,67,91,94,149],"play":[34],"a":[35,45,83,126,185],"central":[36],"role":[37],"building":[39],"ML":[40],"models":[41],"and":[42,70,74,85,93,115,137,171,211],"there":[43],"is":[44,182],"need":[46],"to":[47,167,189,224],"focus":[48],"on":[49],"data-centric":[50],"AI":[51,97],"innovations.":[52],"In":[53],"this":[54,203],"article,":[55],"we":[56,124],"first":[57,155,209],"map":[58],"steps":[60,98],"taken":[61],"scientists":[64],"preparation":[68],"phase":[69],"identify":[71],"open":[72,112],"areas":[73],"pain":[75,101],"points":[76,102],"via":[77,144],"user":[78,104,146],"interviews.":[79,105],"We":[80,106,151],"then":[81],"propose":[82],"framework":[84],"four":[86],"novel":[87],"algorithms":[88,110,136,143],"exploratory":[90],"analysis":[92],"quality":[95],"addressing":[99],"from":[103,153,202],"also":[107],"validate":[108],"our":[109,120],"source":[113],"datasets":[114],"show":[116,212],"effectiveness":[118],"proposed":[121],"methods.":[122],"Next,":[123],"build":[125],"tool":[127,164,193],"that":[128,158,220],"automatically":[129],"generates":[130],"python":[131],"code":[132],"encompassing":[133],"above":[135],"study":[138,156,181,204,210],"usefulness":[140],"these":[142],"two":[145],"studies":[147],"scientists.":[150],"observe":[152],"results":[157,201],"participants":[160],"who":[161],"used":[162,196],"were":[165],"able":[166],"gain":[168],"2\u00d7":[169],"productivity":[170],"6%":[172],"model":[173],"improvement":[174],"over":[175],"control":[177],"group.":[178],"The":[179,200],"second":[180],"performed":[183],"more":[186],"realistic":[187],"environment":[188],"understand":[190],"how":[191],"would":[194],"be":[195,222],"real-world":[198],"scenarios.":[199],"are":[205],"coherent":[206],"average":[214],"30\u201350%":[216],"time":[218],"savings":[219],"can":[221],"attributed":[223],"tool.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":8}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}