{"id":"https://openalex.org/W3013451997","doi":"https://doi.org/10.48550/arxiv.1912.10389","title":"Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning","display_name":"Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning","publication_year":2019,"publication_date":"2019-12-22","ids":{"openalex":"https://openalex.org/W3013451997","doi":"https://doi.org/10.48550/arxiv.1912.10389","mag":"3013451997"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1912.10389","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.10389","pdf_url":"https://arxiv.org/pdf/1912.10389","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.10389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109444700","display_name":"Eun Seo Jo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jo, Eun Seo","raw_affiliation_strings":["Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089275971","display_name":"Timnit Gebru","orcid":"https://orcid.org/0009-0007-4814-1944","observed_orcids":["https://orcid.org/0009-0007-4814-1944"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gebru, Timnit","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9976000189781189,"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":0.9976000189781189,"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/T14201","display_name":"Data Analysis and Archiving","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-collection","display_name":"data collection","score":0.7519999742507935},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.7260000109672546},{"id":"https://openalex.org/keywords/archives","display_name":"archives","score":0.7490000128746033},{"id":"https://openalex.org/keywords/libraries","display_name":"libraries","score":0.703000009059906},{"id":"https://openalex.org/keywords/fairness","display_name":"fairness","score":0.3070000112056732},{"id":"https://openalex.org/keywords/accountability","display_name":"accountability","score":0.7839999794960022},{"id":"https://openalex.org/keywords/transparency","display_name":"transparency","score":0.9490000009536743},{"id":"https://openalex.org/keywords/ethics","display_name":"ethics","score":0.8119999766349792},{"id":"https://openalex.org/keywords/privacy","display_name":"privacy","score":0.7739999890327454},{"id":"https://openalex.org/keywords/consent","display_name":"consent","score":0.8199999928474426},{"id":"https://openalex.org/keywords/power","display_name":"power","score":0.593999981880188},{"id":"https://openalex.org/keywords/inclusiveness","display_name":"inclusivity","score":0.9750000238418579}],"concepts":[{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.7461850047111511},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.7350072264671326},{"id":"https://openalex.org/C196187386","wikidata":"https://www.wikidata.org/wiki/Q1050187","display_name":"Sociocultural evolution","level":2,"score":0.6881074905395508},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.6597256660461426},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49416306614875793},{"id":"https://openalex.org/C2775922551","wikidata":"https://www.wikidata.org/wiki/Q7135033","display_name":"Parallels","level":2,"score":0.4797033667564392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44560444355010986},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.31917694211006165},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2404351532459259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14656254649162292},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.14381751418113708},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11734947562217712},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08520367741584778},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1912.10389","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.10389","pdf_url":"https://arxiv.org/pdf/1912.10389","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.1912.10389","doi":"https://doi.org/10.48550/arxiv.1912.10389","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.10389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.10389","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.10389","pdf_url":"https://arxiv.org/pdf/1912.10389","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":0.7390999794006348,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W564648941","https://openalex.org/W589067101","https://openalex.org/W604552494","https://openalex.org/W1953183316","https://openalex.org/W1975739711","https://openalex.org/W2019502441","https://openalex.org/W2088911157","https://openalex.org/W2093647425","https://openalex.org/W2093746228","https://openalex.org/W2131817520","https://openalex.org/W2192658426","https://openalex.org/W2211426880","https://openalex.org/W2597730742","https://openalex.org/W2600853029","https://openalex.org/W2766202288","https://openalex.org/W2769358515","https://openalex.org/W2795038878","https://openalex.org/W2795908329","https://openalex.org/W2897042519","https://openalex.org/W2897154134","https://openalex.org/W2898015613","https://openalex.org/W2912457762","https://openalex.org/W2953522645","https://openalex.org/W3099361686"],"related_works":["https://openalex.org/W4288083800","https://openalex.org/W7220052650","https://openalex.org/W3112501082","https://openalex.org/W4392543448","https://openalex.org/W4318225411","https://openalex.org/W7084045532","https://openalex.org/W3043315258","https://openalex.org/W2979417040","https://openalex.org/W4386185505","https://openalex.org/W2765146466"],"abstract_inverted_index":{"A":[0],"growing":[1],"body":[2],"of":[3,32,43],"work":[4],"shows":[5],"that":[6,54,63,74,145],"many":[7,117],"problems":[8],"in":[9,15,21,139,143,150,171],"fairness,":[10],"accountability,":[11],"transparency,":[12,128],"and":[13,27,71,78,90,103,111,115,129,169,174],"ethics":[14,130],"machine":[16,45],"learning":[17,46],"systems":[18],"are":[19,93],"rooted":[20],"decisions":[22],"surrounding":[23],"the":[24,44,94,109],"data":[25,37,69,121,148,155,172],"collection":[26,38,70,122,141,149,156,173],"annotation":[28],"process.":[29],"In":[30,49],"spite":[31],"its":[33],"fundamental":[34],"nature":[35],"however,":[36],"remains":[39],"an":[40],"overlooked":[41],"part":[42],"(ML)":[47],"pipeline.":[48],"this":[50],"paper,":[51],"we":[52,161],"argue":[53],"a":[55],"new":[56],"specialization":[57],"should":[58],"be":[59,86,166],"formed":[60],"within":[61],"ML":[62,163],"is":[64],"focused":[65],"on":[66],"methodologies":[67],"for":[68,81],"annotation:":[72],"efforts":[73],"require":[75],"institutional":[76],"frameworks":[77],"procedures.":[79],"Specifically":[80],"sociocultural":[82,151],"data,":[83],"parallels":[84],"can":[85,146],"drawn":[87],"from":[88,158,176],"archives":[89,144],"libraries.":[91],"Archives":[92],"longest":[95],"standing":[96],"communal":[97],"effort":[98],"to":[99,113,120,165],"gather":[100],"human":[101],"information":[102],"archive":[104],"scholars":[105],"have":[106],"already":[107],"developed":[108],"language":[110],"procedures":[112],"address":[114],"discuss":[116,134],"challenges":[118],"pertaining":[119],"such":[123],"as":[124],"consent,":[125],"power,":[126],"inclusivity,":[127],"&":[131],"privacy.":[132],"We":[133],"these":[135],"five":[136],"key":[137],"approaches":[138],"document":[140],"practices":[142,157],"inform":[147],"ML.":[152],"By":[153],"showing":[154],"another":[159],"field,":[160],"encourage":[162],"research":[164],"more":[167],"cognizant":[168],"systematic":[170],"draw":[175],"interdisciplinary":[177],"expertise.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":43},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-04-03T00:00:00"}
