{"id":"https://openalex.org/W3119940315","doi":"https://doi.org/10.1145/3411764.3445526","title":"AutoDS: Towards Human-Centered Automation of Data Science","display_name":"AutoDS: Towards Human-Centered Automation of Data Science","publication_year":2021,"publication_date":"2021-05-06","ids":{"openalex":"https://openalex.org/W3119940315","doi":"https://doi.org/10.1145/3411764.3445526","mag":"3119940315"},"language":"en","primary_location":{"id":"doi:10.1145/3411764.3445526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411764.3445526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.05273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062817658","display_name":"Dakuo Wang","orcid":"https://orcid.org/0000-0001-9371-9441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dakuo Wang","raw_affiliation_strings":["IBM Research, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086240513","display_name":"Josh Andr\u00e9s","orcid":"https://orcid.org/0000-0001-5882-3139"},"institutions":[{"id":"https://openalex.org/I4210120068","display_name":"IBM Research - Australia","ror":"https://ror.org/027r3nx49","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210120068"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Josh Andres","raw_affiliation_strings":["IBM Research Australia, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Australia, Australia","institution_ids":["https://openalex.org/I4210120068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011883289","display_name":"Justin D. Weisz","orcid":"https://orcid.org/0000-0003-2228-2398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Justin D. Weisz","raw_affiliation_strings":["IBM Research AI, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079903977","display_name":"Erick Oduor","orcid":"https://orcid.org/0009-0003-0548-6193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erick Oduor","raw_affiliation_strings":["IBM Research Africa, Kenya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Africa, Kenya","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082995130","display_name":"Casey Dugan","orcid":"https://orcid.org/0000-0002-1508-2091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Casey Dugan","raw_affiliation_strings":["IBM Research, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9878000020980835,"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/T10260","display_name":"Software Engineering Research","score":0.9871000051498413,"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/automation","display_name":"Automation","score":0.7296919226646423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7080377340316772},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7064982056617737},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6845875978469849},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.4548344016075134},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4526233673095703},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44312500953674316},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.43779370188713074},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.385434091091156},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.31051695346832275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29394274950027466},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18886086344718933},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1302197277545929}],"concepts":[{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.7296919226646423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080377340316772},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7064982056617737},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6845875978469849},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4548344016075134},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4526233673095703},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44312500953674316},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.43779370188713074},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.385434091091156},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31051695346832275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29394274950027466},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18886086344718933},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1302197277545929},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3411764.3445526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411764.3445526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.05273","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05273","pdf_url":"https://arxiv.org/pdf/2101.05273","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.05273","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05273","pdf_url":"https://arxiv.org/pdf/2101.05273","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"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W148615303","https://openalex.org/W362765048","https://openalex.org/W603221366","https://openalex.org/W1501005121","https://openalex.org/W1902040647","https://openalex.org/W2005219594","https://openalex.org/W2032843080","https://openalex.org/W2042659035","https://openalex.org/W2043498719","https://openalex.org/W2059216172","https://openalex.org/W2064766209","https://openalex.org/W2084812512","https://openalex.org/W2097273107","https://openalex.org/W2101234009","https://openalex.org/W2125791475","https://openalex.org/W2131737623","https://openalex.org/W2132667707","https://openalex.org/W2156897926","https://openalex.org/W2182353144","https://openalex.org/W2182361439","https://openalex.org/W2404399993","https://openalex.org/W2502657205","https://openalex.org/W2557007068","https://openalex.org/W2584335703","https://openalex.org/W2591734415","https://openalex.org/W2621019965","https://openalex.org/W2771189628","https://openalex.org/W2795916109","https://openalex.org/W2796040126","https://openalex.org/W2809161078","https://openalex.org/W2886851211","https://openalex.org/W2893478583","https://openalex.org/W2899601017","https://openalex.org/W2903808828","https://openalex.org/W2913615284","https://openalex.org/W2916292150","https://openalex.org/W2916904544","https://openalex.org/W2941332886","https://openalex.org/W2941455863","https://openalex.org/W2941766203","https://openalex.org/W2947123069","https://openalex.org/W2949941638","https://openalex.org/W2954185371","https://openalex.org/W2971867419","https://openalex.org/W2972072326","https://openalex.org/W2995482541","https://openalex.org/W2997686802","https://openalex.org/W2998732476","https://openalex.org/W3029504795","https://openalex.org/W3094264786","https://openalex.org/W3099545035","https://openalex.org/W3106372104","https://openalex.org/W3111170813","https://openalex.org/W3112020351","https://openalex.org/W3120083395","https://openalex.org/W3120370895","https://openalex.org/W3121784008","https://openalex.org/W3123491306","https://openalex.org/W3157506384","https://openalex.org/W3160903453","https://openalex.org/W4248101078","https://openalex.org/W4254114958","https://openalex.org/W4288083546","https://openalex.org/W4289123308","https://openalex.org/W4297823417","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2350278424","https://openalex.org/W2071432835","https://openalex.org/W4239401009","https://openalex.org/W3169941283","https://openalex.org/W3081133439","https://openalex.org/W4386246791","https://openalex.org/W2945537679","https://openalex.org/W3211701140","https://openalex.org/W2952280724","https://openalex.org/W2133103607"],"abstract_inverted_index":{"Data":[0,67],"science":[1,65,132,156,205],"(DS)":[2],"projects":[3],"often":[4],"follow":[5],"a":[6,99,105,115,130,154],"lifecycle":[7],"that":[8,53,167],"consists":[9],"of":[10,118,123],"laborious":[11],"tasks":[12],"for":[13,195],"data":[14,20,38,64,131,140,155,204],"scientists":[15],"and":[16,87,104,121,147,178],"domain":[17],"experts":[18],"(e.g.,":[19],"exploration,":[21],"model":[22],"training,":[23],"etc.).":[24],"Only":[25],"till":[26],"recently,":[27],"machine":[28,49],"learning(ML)":[29],"researchers":[30],"have":[31,175],"developed":[32],"promising":[33],"automation":[34,60,197],"techniques":[35,61,198],"to":[36,55,62,71,95,113,152],"aid":[37],"workers":[39,68],"in":[40,128,202],"these":[41],"tasks.":[42],"This":[43],"paper":[44],"introduces":[45],"AutoDS,":[46,146],"an":[47,125],"automated":[48],"learning":[50],"(AutoML)":[51],"system":[52,77,127],"aims":[54],"leverage":[56],"the":[57,76,89,96,148,168,172,189,203],"latest":[58],"ML":[59,81],"support":[63],"projects.":[66],"only":[69],"need":[70],"upload":[72],"their":[73],"dataset,":[74],"then":[75],"can":[78],"automatically":[79],"suggest":[80],"configurations,":[82],"preprocess":[83],"data,":[84],"select":[85],"algorithm,":[86],"train":[88],"model.":[90],"These":[91],"suggestions":[92],"are":[93],"presented":[94],"user":[97,102,108,119],"via":[98],"web-based":[100],"graphical":[101],"interface":[103],"notebook-based":[106],"programming":[107],"interface.":[109],"Our":[110],"goal":[111],"is":[112],"offer":[114],"systematic":[116],"investigation":[117],"interaction":[120],"perceptions":[122],"using":[124],"AutoDS":[126,136,160,173],"solving":[129],"task.":[133],"We":[134,186],"studied":[135],"with":[137],"30":[138],"professional":[139],"scientists,":[141],"where":[142],"one":[143],"group":[144,174],"used":[145],"other":[149],"did":[150],"not,":[151],"complete":[153],"project.":[157],"As":[158],"expected,":[159],"improves":[161],"productivity;":[162],"Yet":[163],"surprisingly,":[164],"we":[165],"find":[166],"models":[169],"produced":[170],"by":[171,191],"higher":[176],"quality":[177],"less":[179],"errors,":[180],"but":[181],"lower":[182],"human":[183,200],"confidence":[184],"scores.":[185],"reflect":[187],"on":[188],"findings":[190],"presenting":[192],"design":[193],"implications":[194],"incorporating":[196],"into":[199],"work":[201],"lifecycle.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":11}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}