{"id":"W2407086192","doi":"10.2196/mental.4822","title":"Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality","year":2016,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Mental Health via Writing","field":"Psychology","cited_by":199,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Algorithm; Artificial intelligence; Computer science; Social media; Predictive value; Suicide prevention; Poison control; Medicine; Medical emergency; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003363708,0.000253758,0.0005089953,0.0001265251,0.0003909152,0.00002226737,0.0005678778,0.0001106581,0.0003317996],"category_scores_gemma":[0.0001222799,0.0001984671,0.00007699811,0.0001858675,0.0001014749,0.0002730226,0.0003020258,0.0002562304,0.00004544244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003896254,"about_ca_system_score_gemma":0.0001556557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001719931,"about_ca_topic_score_gemma":0.0001649188,"domain_scores_codex":[0.9961838,0.0006236432,0.001071909,0.0007658952,0.0004457904,0.0009089902],"domain_scores_gemma":[0.9975891,0.0004445691,0.000707802,0.0008852876,0.0000622408,0.0003110333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005979958,0.0006716048,0.08187787,0.001061174,0.00009056078,0.00000494096,0.007958653,7.875872e-7,0.005007877,0.0004915515,0.01639687,0.8858401],"study_design_scores_gemma":[0.07927348,0.01319019,0.3679335,0.01031775,0.0001633936,0.0003464338,0.07223562,0.00906,0.03184411,0.002058272,0.4079035,0.005673759],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698573,0.00131883,0.006855312,0.008344877,0.001913518,0.004800532,0.002639622,0.0003050806,0.003964944],"genre_scores_gemma":[0.9894275,0.00004663307,0.005764189,0.001914362,0.0003222507,0.0002222594,0.0009836589,0.00007584957,0.00124328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8801664,"threshold_uncertainty_score":0.8093252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1912130276026938,"score_gpt":0.4545913416383931,"score_spread":0.2633783140356993,"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."}}