{"id":"https://openalex.org/W4409544796","doi":"https://doi.org/10.1140/epjds/s13688-025-00541-1","title":"Whose voice matters? Word embeddings reveal identity bias in news quotes","display_name":"Whose voice matters? Word embeddings reveal identity bias in news quotes","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W4409544796","doi":"https://doi.org/10.1140/epjds/s13688-025-00541-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/40256399"},"language":"en","primary_location":{"id":"doi:10.1140/epjds/s13688-025-00541-1","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-025-00541-1","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-025-00541-1","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"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":"EPJ Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-025-00541-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107604808","display_name":"Nnaemeka Ohamadike","orcid":null},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Nnaemeka Ohamadike","raw_affiliation_strings":["Centre for Applied Data Science, University of Johannesburg, Johannesburg, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Applied Data Science, University of Johannesburg, Johannesburg, South Africa","institution_ids":["https://openalex.org/I24027795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067132253","display_name":"Kevin Durrheim","orcid":"https://orcid.org/0000-0003-2926-5953"},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Kevin Durrheim","raw_affiliation_strings":["Department of Psychology, University of Johannesburg, Johannesburg, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Johannesburg, Johannesburg, South Africa","institution_ids":["https://openalex.org/I24027795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040968407","display_name":"Mpho Primus","orcid":"https://orcid.org/0000-0002-5270-3619"},"institutions":[{"id":"https://openalex.org/I24027795","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17","country_code":"ZA","type":"education","lineage":["https://openalex.org/I24027795"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Mpho Primus","raw_affiliation_strings":["Institute for Artificial Intelligence Systems, University of Johannesburg, Johannesburg, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence Systems, University of Johannesburg, Johannesburg, South Africa","institution_ids":["https://openalex.org/I24027795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1190,"currency":"GBP","value_usd":1459},"apc_paid":{"value":1190,"currency":"GBP","value_usd":1459},"fwci":12.0047,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97991212,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"14","issue":"1","first_page":"30","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21459999680519104,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21459999680519104,"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/T13718","display_name":"Media Influence and Politics","score":0.10080000013113022,"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/T10133","display_name":"Media Studies and Communication","score":0.062300000339746475,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/word","display_name":"Word (group theory)","score":0.6932645440101624},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6289793252944946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5249509811401367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4508476257324219},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3469100594520569},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3217325806617737},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3163158595561981},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17016848921775818},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16312697529792786},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11903077363967896}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6932645440101624},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6289793252944946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5249509811401367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4508476257324219},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3469100594520569},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3217325806617737},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3163158595561981},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17016848921775818},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16312697529792786},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11903077363967896}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1140/epjds/s13688-025-00541-1","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-025-00541-1","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-025-00541-1","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"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":"EPJ Data Science","raw_type":"journal-article"},{"id":"pmid:40256399","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40256399","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EPJ data science","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12006212","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12006212","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12006212/pdf/13688_2025_Article_541.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EPJ Data Sci","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:a7cc46117aef42ba92b320a351f6e2fd","is_oa":true,"landing_page_url":"https://doaj.org/article/a7cc46117aef42ba92b320a351f6e2fd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EPJ Data Science, Vol 14, Iss 1, Pp 1-18 (2025)","raw_type":"article"},{"id":"pmh:oai:share.osf.io:b1a2d3fc-4ee2-4e85-9d33-0f31714d7d57","is_oa":false,"landing_page_url":"https://osf.io/xd7bz","pdf_url":null,"source":{"id":"https://openalex.org/S4306401127","display_name":"OSF Preprints (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"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":"Project"}],"best_oa_location":{"id":"doi:10.1140/epjds/s13688-025-00541-1","is_oa":true,"landing_page_url":"https://doi.org/10.1140/epjds/s13688-025-00541-1","pdf_url":"https://epjdatascience.springeropen.com/counter/pdf/10.1140/epjds/s13688-025-00541-1","source":{"id":"https://openalex.org/S2504380752","display_name":"EPJ Data Science","issn_l":"2193-1127","issn":["2193-1127"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"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":"EPJ Data Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G1820455297","display_name":"Developmental Change and Individual Differences in Sensory Discrimination and Working Memory: The Impact and Interplay of Chronological Age and Human Intelligence","funder_award_id":"137755","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6199665532","display_name":null,"funder_award_id":"10001AL_205032","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8208409376","display_name":null,"funder_award_id":"137755","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323959","display_name":"University of Johannesburg","ror":"https://ror.org/04z6c2n17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409544796.pdf","grobid_xml":"https://content.openalex.org/works/W4409544796.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W431301655","https://openalex.org/W611653470","https://openalex.org/W1551153090","https://openalex.org/W1977214969","https://openalex.org/W2025472087","https://openalex.org/W2034650052","https://openalex.org/W2047444021","https://openalex.org/W2085814394","https://openalex.org/W2087136682","https://openalex.org/W2095338143","https://openalex.org/W2103843299","https://openalex.org/W2104334311","https://openalex.org/W2114497837","https://openalex.org/W2114621402","https://openalex.org/W2223092947","https://openalex.org/W2559655401","https://openalex.org/W2609975453","https://openalex.org/W2769358515","https://openalex.org/W2794635328","https://openalex.org/W2808860760","https://openalex.org/W2889326414","https://openalex.org/W2893425640","https://openalex.org/W2907371389","https://openalex.org/W2912935992","https://openalex.org/W2948471640","https://openalex.org/W2966775979","https://openalex.org/W3009728556","https://openalex.org/W3038872819","https://openalex.org/W3047369131","https://openalex.org/W3103365499","https://openalex.org/W4243926000","https://openalex.org/W4251480583","https://openalex.org/W4283738815","https://openalex.org/W4283818176","https://openalex.org/W4286792058","https://openalex.org/W4289934353","https://openalex.org/W4294612484","https://openalex.org/W4299829301","https://openalex.org/W4300471810","https://openalex.org/W4300764384","https://openalex.org/W4309741879","https://openalex.org/W4310576795","https://openalex.org/W4319770256","https://openalex.org/W4386191025","https://openalex.org/W4386892854","https://openalex.org/W4387096891","https://openalex.org/W4390234368","https://openalex.org/W4402379300","https://openalex.org/W4409476215","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298","https://openalex.org/W2600246793"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"identity":[3],"bias":[4,21,29,72,122],"(gender":[5],"and":[6,14,27,43,70,76,97,110,120,127,139,143,188],"race)":[7],"in":[8,30,73,114,123,162,198],"the":[9,48,124,163,193,199],"South":[10,31,35,57,91],"African":[11,32,58,92],"news":[12,52,59,74,93,125,164],"selection":[13,75,126],"representation":[15],"of":[16,78,129],"COVID-19":[17],"vaccination":[18,87,145],"quotes.":[19,79],"Social":[20],"studies":[22,40],"have":[23],"qualitatively":[24],"examined":[25,68],"race":[26,69,121],"gender":[28,71,119],"news,":[33],"given":[34],"Africa's":[36],"apartheid":[37],"history;":[38],"yet,":[39],"that":[41,179],"examine":[42],"quantify":[44],"these":[45,190],"biases":[46,112,172,191],"at":[47,192,210],"speaker":[49,196],"level":[50,197],"using":[51],"quotes":[53,88,130],"from":[54,89],"a":[55,182],"representative":[56],"corpus":[60],"remain":[61],"limited.":[62],"To":[63],"address":[64],"this":[65],"gap,":[66],"we":[67,177],"framing":[77,128],"We":[80],"used":[81],"word":[82],"embedding":[83],"trained":[84],"on":[85],"22,627":[86],"76":[90],"sources":[94],"between":[95],"2020":[96],"2023.":[98],"These":[99],"large-scale":[100],"processing":[101],"embeddings":[102,180],"are":[103,173],"unbiased":[104],"by":[105],"design":[106],"but":[107,147],"can":[108],"learn":[109],"uncover":[111],"hidden":[113],"language.":[115],"Our":[116],"findings":[117],"reveal":[118],"-":[131],"journalists":[132],"privilege":[133],"White":[134],"voices":[135,150],"as":[136],"more":[137,160],"authoritative":[138],"connected":[140],"to":[141,151,185],"global":[142],"technical":[144],"discourse":[146],"confine":[148],"black":[149],"primarily":[152],"localised":[153],"contexts.":[154],"They":[155],"also":[156],"quote":[157],"male":[158],"speakers":[159],"frequently":[161],"than":[165],"females.":[166],"In":[167],"an":[168],"era":[169],"where":[170],"human":[171],"becoming":[174],"increasingly":[175],"implicit,":[176],"argue":[178],"offer":[181],"robust":[183],"tool":[184],"unearth,":[186],"monitor,":[187],"evaluate":[189],"micro":[194],"or":[195],"news.":[200],"Supplementary":[201],"Information:":[202],"The":[203],"online":[204],"version":[205],"contains":[206],"supplementary":[207],"material":[208],"available":[209],"10.1140/epjds/s13688-025-00541-1.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
