{"id":"W3101628588","doi":"10.1371/journal.pone.0241239","title":"A machine learning approach to predict ethnicity using personal name and census location in Canada","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Names, Identity, and Discrimination Research","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; University of Alberta; Government of Canada; Alberta Machine Intelligence Institute","keywords":"Census; Ethnic group; Artificial intelligence; Substring; Support vector machine; Population; Machine learning; Computer science; Logistic regression; Demography; Set (abstract data type); Sociology; Political science; Law","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":[0.0003180804,0.00004617123,0.00009704478,0.00004706422,0.0002337817,0.00005163418,0.00008606581,0.00002736919,0.00003723707],"category_scores_gemma":[0.0009756904,0.00005128969,0.000007837371,0.0003670776,0.00005053794,0.00009088436,0.00004962164,0.0001800704,0.000001889267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003276081,"about_ca_system_score_gemma":0.000658312,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9223898,"about_ca_topic_score_gemma":0.8144602,"domain_scores_codex":[0.9987566,0.000177914,0.00009402631,0.0001657603,0.0006203055,0.0001853176],"domain_scores_gemma":[0.9996071,0.00004458622,0.0000251922,0.00003014735,0.0001042775,0.0001886316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000560591,0.0004361609,0.9598001,0.0003542909,0.00003862489,0.000009004108,0.03380376,0.0008323931,0.0010227,0.001069809,0.0001918293,0.002385275],"study_design_scores_gemma":[0.001127855,0.0001555753,0.290762,0.0001603616,0.0000814603,7.70416e-7,0.03749444,0.6684573,0.0002307939,0.0001895965,0.0008793032,0.0004605527],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922572,0.0002632419,0.0001847572,0.0028166,0.00001116379,0.0002259783,0.00001084617,0.00001650455,0.004213651],"genre_scores_gemma":[0.9989644,0.00004648964,0.0005332712,0.0001725198,0.0000818015,0.000006856258,0.000009683924,0.00000488419,0.0001801449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6690381,"threshold_uncertainty_score":0.2091533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1537226894422716,"score_gpt":0.3131259734773718,"score_spread":0.1594032840351002,"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."}}