{"id":"W3125724250","doi":"10.1371/journal.pone.0245533","title":"The Gender Gap Tracker: Using Natural Language Processing to measure gender bias in media","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Media Influence and Politics","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Simon Fraser University","keywords":"Set (abstract data type); Gender gap; Computer science; BitTorrent tracker; Tracking (education); Gender bias; Social media; Natural language processing; Artificial intelligence; Data science; Psychology; World Wide Web; Social psychology; Eye tracking","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007121448,0.00008543931,0.0001385414,0.00004440063,0.0003573585,0.000138079,0.0001937725,0.00008191387,0.00007867551],"category_scores_gemma":[0.002236157,0.00006779771,0.00002977094,0.0004408234,0.000104704,0.0001559945,0.00003372571,0.0002378529,0.00004167735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001077465,"about_ca_system_score_gemma":0.0005541446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003310548,"about_ca_topic_score_gemma":0.004005547,"domain_scores_codex":[0.9982433,0.0002198331,0.0001785367,0.0001705527,0.0007405365,0.000447262],"domain_scores_gemma":[0.9991996,0.0002684894,0.00004388225,0.0001525122,0.0001911191,0.0001443869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003093145,0.0006278717,0.0528736,0.0002341866,0.000143927,0.0002534279,0.8709459,0.00003093665,0.04567396,0.006752523,0.0004669765,0.02196576],"study_design_scores_gemma":[0.00251405,0.00006208668,0.08408002,0.002221271,0.0007048667,0.00002362475,0.7749775,0.004515267,0.1034439,0.01227019,0.0124191,0.002768133],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869975,0.004875649,0.000007202936,0.001316996,0.000169198,0.0001614748,0.000004192411,0.0000334019,0.006434321],"genre_scores_gemma":[0.9964954,0.00006976426,0.001349641,0.001150985,0.0005890365,0.00001069204,0.00000329697,0.0000115899,0.0003196296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09596837,"threshold_uncertainty_score":0.276471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3544154494667636,"score_gpt":0.3688718947842602,"score_spread":0.01445644531749662,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}