{"id":"https://openalex.org/W7161155166","doi":"https://doi.org/10.1145/3805689.3812411","title":"Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development","display_name":"Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7161155166","doi":"https://doi.org/10.1145/3805689.3812411"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3812411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3812411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071400231","display_name":"Eshta Bhardwaj","orcid":"https://orcid.org/0000-0001-8523-5201"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eshta Bhardwaj","raw_affiliation_strings":["Faculty of Information, University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0001-8523-5201","affiliations":[{"raw_affiliation_string":"Faculty of Information, University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065203672","display_name":"Ciara Zogheib","orcid":"https://orcid.org/0000-0002-0620-3007"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ciara Zogheib","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0620-3007","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136133931","display_name":"Christoph Becker","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christoph Becker","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8364-0593","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6903","last_page":"6955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.12880000472068787,"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"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.12880000472068787,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.12250000238418579,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.11969999969005585,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reflexivity","display_name":"Reflexivity","score":0.8938000202178955},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.8773999810218811},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4959999918937683},{"id":"https://openalex.org/keywords/thematic-analysis","display_name":"Thematic analysis","score":0.3862000107765198}],"concepts":[{"id":"https://openalex.org/C13200473","wikidata":"https://www.wikidata.org/wiki/Q2747831","display_name":"Reflexivity","level":2,"score":0.8938000202178955},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.8773999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230999827384949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.3862000107765198},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805689.3812411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.11345","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.11345","pdf_url":"https://arxiv.org/pdf/2605.11345","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,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805689.3812411","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812411","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.6795492172241211}],"awards":[{"id":"https://openalex.org/G4550914251","display_name":null,"funder_award_id":"RGPIN-2016","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6215366036","display_name":null,"funder_award_id":"RGPIN-2025-07063","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"It":[0],"is":[1,10,64,69,113,127],"prominently":[2],"recognized":[3],"that":[4,125],"dataset":[5,32,60,78,140],"development":[6],"in":[7,41,59,115,138,179],"machine":[8],"learning":[9],"a":[11,65,128,151,162],"value-laden":[12],"process":[13],"from":[14,83],"problem":[15],"formulation":[16],"to":[17,38,50,56,73,109,168],"data":[18,29],"processing,":[19],"use,":[20],"and":[21,31,72,88,90,105,119,143,160,178],"reuse.":[22],"Structured":[23],"documentation":[24,79,117,141,176],"frameworks":[25,80,96,118,142,177],"such":[26],"as":[27],"datasheets,":[28],"statements,":[30],"nutrition":[33],"labels":[34],"have":[35],"been":[36],"created":[37],"aid":[39],"developers":[40],"documenting":[42],"how":[43,111],"their":[44,120],"datasets":[45],"were":[46],"produced":[47],"and,":[48],"according":[49],"the":[51,54,92,95,180],"creators":[52],"of":[53,94,131,136,146,153,164],"frameworks,":[55],"facilitate":[57],"reflexivity":[58,63,84,112,137,155],"development.":[61],"While":[62],"stated":[66],"goal,":[67],"it":[68],"unclear":[70],"whether":[71,91],"what":[74],"extent":[75],"these":[76,147,172],"structured":[77,116,175],"incorporate":[81,171],"concepts":[82],"literature":[85],"(at":[86],"FAccT":[87,181],"elsewhere)":[89],"use":[93],"demonstrates":[97],"reflexivity.":[98],"Here,":[99],"we":[100],"adopt":[101],"mixed-method":[102],"thematic":[103],"analysis":[104,108],"corpus-assisted":[106],"discourse":[107],"explore":[110],"incorporated":[114],"responses.":[121],"We":[122,149],"demonstrate":[123],"empirically":[124],"there":[126],"general":[129],"lack":[130],"engagement":[132],"with":[133],"major":[134,154],"themes":[135],"both":[139],"published":[144],"applications":[145],"frameworks.":[148],"present":[150],"codebook":[152],"topics,":[156],"recommend":[157],"actionable":[158],"strategies,":[159],"propose":[161],"set":[163],"extended":[165],"datasheet":[166],"questions":[167],"more":[169],"effectively":[170],"topics":[173],"into":[174],"literature.":[182]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-15T00:00:00"}