{"id":"https://openalex.org/W4327743697","doi":"https://doi.org/10.1145/3588433","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","display_name":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","publication_year":2023,"publication_date":"2023-03-17","ids":{"openalex":"https://openalex.org/W4327743697","doi":"https://doi.org/10.1145/3588433"},"language":"en","primary_location":{"id":"doi:10.1145/3588433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588433","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032735930","display_name":"Nima Shahbazi","orcid":"https://orcid.org/0000-0001-7016-3807"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Shahbazi","raw_affiliation_strings":["University of Illinois Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0001-7016-3807","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846771","display_name":"Lin Yin","orcid":"https://orcid.org/0000-0002-6609-5706"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Lin","raw_affiliation_strings":["University of Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-6609-5706","affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027319416","display_name":"Abolfazl Asudeh","orcid":"https://orcid.org/0000-0002-5251-6186"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abolfazl Asudeh","raw_affiliation_strings":["University of Illinois Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0002-5251-6186","affiliations":[{"raw_affiliation_string":"University of Illinois Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090550596","display_name":"H. V. Jagadish","orcid":"https://orcid.org/0000-0003-0724-5214"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0003-0724-5214","affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.1852,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.99644128,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"55","issue":"13s","first_page":"1","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9976999759674072,"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":0.9973999857902527,"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":0.8138701319694519},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5921074748039246},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5844027400016785},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5813822150230408},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5350165963172913},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5124993324279785},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.5041605234146118},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.47774404287338257},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46633362770080566},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.4531722962856293},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42451542615890503},{"id":"https://openalex.org/keywords/survey-data-collection","display_name":"Survey data collection","score":0.4108017683029175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.395659476518631},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34245964884757996},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10376223921775818}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138701319694519},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5921074748039246},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5844027400016785},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5813822150230408},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5350165963172913},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5124993324279785},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.5041605234146118},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.47774404287338257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46633362770080566},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.4531722962856293},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42451542615890503},{"id":"https://openalex.org/C198477413","wikidata":"https://www.wikidata.org/wiki/Q7647069","display_name":"Survey data collection","level":2,"score":0.4108017683029175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.395659476518631},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34245964884757996},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10376223921775818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588433","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5400000214576721},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G2184854824","display_name":null,"funder_award_id":"1934565","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2967473021","display_name":null,"funder_award_id":"1741022, 1934565","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3385564969","display_name":"III: Medium: Collaborative Research: Fairness in Web Database Applications","funder_award_id":"2106176","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3710419309","display_name":null,"funder_award_id":"1741022","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":125,"referenced_works":["https://openalex.org/W78068321","https://openalex.org/W1819662813","https://openalex.org/W1852255964","https://openalex.org/W1991181258","https://openalex.org/W2008291900","https://openalex.org/W2029626238","https://openalex.org/W2031342017","https://openalex.org/W2033193852","https://openalex.org/W2055721472","https://openalex.org/W2073857326","https://openalex.org/W2079966837","https://openalex.org/W2080731889","https://openalex.org/W2086110755","https://openalex.org/W2108598243","https://openalex.org/W2116759751","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2186686397","https://openalex.org/W2187089797","https://openalex.org/W2322132911","https://openalex.org/W2483215953","https://openalex.org/W2487898712","https://openalex.org/W2514617369","https://openalex.org/W2563852449","https://openalex.org/W2791170418","https://openalex.org/W2795975316","https://openalex.org/W2796868841","https://openalex.org/W2804302783","https://openalex.org/W2807251972","https://openalex.org/W2884061367","https://openalex.org/W2888167352","https://openalex.org/W2889624842","https://openalex.org/W2896331720","https://openalex.org/W2909212904","https://openalex.org/W2914097099","https://openalex.org/W2929071855","https://openalex.org/W2947280697","https://openalex.org/W2950888501","https://openalex.org/W2951635356","https://openalex.org/W2962756421","https://openalex.org/W2962770929","https://openalex.org/W2962922665","https://openalex.org/W2963526187","https://openalex.org/W2966133050","https://openalex.org/W2972972637","https://openalex.org/W2982358316","https://openalex.org/W2987103574","https://openalex.org/W2992899357","https://openalex.org/W3004493409","https://openalex.org/W3005040148","https://openalex.org/W3006437051","https://openalex.org/W3012624518","https://openalex.org/W3012819905","https://openalex.org/W3013854004","https://openalex.org/W3023702633","https://openalex.org/W3031292160","https://openalex.org/W3032388710","https://openalex.org/W3034460046","https://openalex.org/W3036567070","https://openalex.org/W3049256904","https://openalex.org/W3082499364","https://openalex.org/W3086663505","https://openalex.org/W3113580345","https://openalex.org/W3120485916","https://openalex.org/W3135890227","https://openalex.org/W3147107444","https://openalex.org/W3158511434","https://openalex.org/W3158735461","https://openalex.org/W3162922192","https://openalex.org/W3168771811","https://openalex.org/W3171842281","https://openalex.org/W3173173856","https://openalex.org/W3173326111","https://openalex.org/W3174324482","https://openalex.org/W3174951300","https://openalex.org/W3174982674","https://openalex.org/W3181414820","https://openalex.org/W3195725782","https://openalex.org/W3197182341","https://openalex.org/W3202615267","https://openalex.org/W3208695477","https://openalex.org/W3210923870","https://openalex.org/W3213556453","https://openalex.org/W3217246256","https://openalex.org/W3217764315","https://openalex.org/W4206323856","https://openalex.org/W4210736086","https://openalex.org/W4211217302","https://openalex.org/W4224080055","https://openalex.org/W4225853030","https://openalex.org/W4226079992","https://openalex.org/W4230414599","https://openalex.org/W4281394649","https://openalex.org/W4281752638","https://openalex.org/W4281811562","https://openalex.org/W4284890692","https://openalex.org/W4287074667","https://openalex.org/W4287322267","https://openalex.org/W4287774713","https://openalex.org/W4288376116","https://openalex.org/W4289534040","https://openalex.org/W4289674280","https://openalex.org/W4289766761","https://openalex.org/W4293431124","https://openalex.org/W4293868193","https://openalex.org/W4297802254","https://openalex.org/W4299805482","https://openalex.org/W4307961097","https://openalex.org/W4322507603","https://openalex.org/W4362714312","https://openalex.org/W4386564359","https://openalex.org/W6638208828","https://openalex.org/W6749630143","https://openalex.org/W6751342375","https://openalex.org/W6751917733","https://openalex.org/W6754412109","https://openalex.org/W6759136097","https://openalex.org/W6771019271","https://openalex.org/W6785254812","https://openalex.org/W6793191273","https://openalex.org/W6798407696","https://openalex.org/W6803324819","https://openalex.org/W6810274832","https://openalex.org/W6811245282","https://openalex.org/W6838476828"],"related_works":["https://openalex.org/W3166594252","https://openalex.org/W1518030604","https://openalex.org/W2426976336","https://openalex.org/W2512741782","https://openalex.org/W2884844053","https://openalex.org/W1516084361","https://openalex.org/W4241973638","https://openalex.org/W2784801669","https://openalex.org/W4253047901","https://openalex.org/W3176915151"],"abstract_inverted_index":{"Data-driven":[0],"algorithms":[1],"are":[2],"only":[3],"as":[4,6,71,109],"good":[5],"the":[7,43,92,101,142,185],"data":[8,26,44,93],"they":[9],"work":[10,190],"with,":[11],"while":[12],"datasets,":[13],"especially":[14],"social":[15],"data,":[16],"often":[17],"fail":[18],"to":[19,30,37,60,127,140,164,180],"represent":[20],"minorities":[21],"adequately.":[22],"Representation":[23],"Bias":[24],"in":[25,42,82,91,170,184],"can":[27],"happen":[28],"due":[29],"various":[31],"reasons,":[32],"ranging":[33],"from":[34],"historical":[35],"discrimination":[36],"selection":[38],"and":[39,46,105,130,150],"sampling":[40],"biases":[41],"acquisition":[45],"preparation":[47],"methods.":[48],"Given":[49],"that":[50,175],"\u201cbias":[51],"in,":[52],"bias":[53,90,108,168],"out,\u201d":[54],"one":[55],"cannot":[56],"expect":[57],"AI-based":[58],"solutions":[59],"have":[61],"equitable":[62],"outcomes":[63],"for":[64],"societal":[65],"applications,":[66],"without":[67],"addressing":[68],"issues":[69,169],"such":[70],"representation":[72,107,167],"bias.":[73],"While":[74],"there":[75],"has":[76,94],"been":[77,95],"extensive":[78],"study":[79],"of":[80,112,116,122,155],"fairness":[81],"machine":[83],"learning":[84],"models,":[85],"including":[86],"several":[87],"review":[88],"papers,":[89],"less":[96],"studied.":[97],"This":[98],"article":[99],"reviews":[100],"literature":[102],"on":[103,146],"identifying":[104],"resolving":[106],"a":[110,113,152,161],"feature":[111],"dataset,":[114],"independent":[115],"how":[117],"consumed":[118],"later.":[119],"The":[120,172],"scope":[121],"this":[123,176],"survey":[124,177],"is":[125,159],"bounded":[126],"structured":[128],"(tabular)":[129],"unstructured":[131],"(e.g.,":[132],"image,":[133],"text,":[134],"graph)":[135],"data.":[136,171],"It":[137],"presents":[138],"taxonomies":[139],"categorize":[141],"studied":[143],"techniques":[144],"based":[145],"multiple":[147],"design":[148],"dimensions":[149],"provides":[151],"side-by-side":[153],"comparison":[154],"their":[156,192],"properties.":[157],"There":[158],"still":[160],"long":[162],"way":[163],"fully":[165],"address":[166],"authors":[173],"hope":[174],"motivates":[178],"researchers":[179],"approach":[181],"these":[182],"challenges":[183],"future":[186],"by":[187],"observing":[188],"existing":[189],"within":[191],"respective":[193],"domains.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}