{"id":"W2127984563","doi":"10.2196/mental.4227","title":"Identifying Chinese Microblog Users With High Suicide Probability Using Internet-Based Profile and Linguistic Features: Classification Model","year":2015,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Mental Health via Writing","field":"Psychology","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fogarty International Center","keywords":"Random forest; Microblogging; Social media; Logistic regression; Computer science; Machine learning; Artificial intelligence; The Internet; Natural language processing; Sample (material); Metric (unit); Psychology; Engineering; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008932325,0.0002953902,0.000367441,0.0001439874,0.0002531696,0.00006020219,0.000168013,0.0001239277,0.00003345236],"category_scores_gemma":[0.00003658761,0.0002566894,0.00003523621,0.0002506645,0.000158771,0.0001247226,0.00007090259,0.0003862141,0.00002397924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001275282,"about_ca_system_score_gemma":0.0004626888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004267931,"about_ca_topic_score_gemma":0.0009974166,"domain_scores_codex":[0.9974039,0.0003184558,0.0005911169,0.000706961,0.0003301055,0.0006494198],"domain_scores_gemma":[0.998525,0.00006459879,0.0004078006,0.0004045689,0.00009494641,0.0005030816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009596359,0.004575545,0.8067714,0.009764887,0.0001978706,0.00008430583,0.1193729,0.0007050298,0.01037343,0.01245998,0.007542095,0.01855622],"study_design_scores_gemma":[0.02117136,0.004045748,0.7318301,0.004205849,0.00008441637,0.0006443062,0.01728864,0.2122571,0.001126043,0.004774429,0.0003903414,0.00218165],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938269,0.0004583133,0.001323791,0.00058298,0.0004400586,0.002518817,0.00007863684,0.0001387387,0.0006318192],"genre_scores_gemma":[0.9674439,0.000002133451,0.03034802,0.001252375,0.0001079942,0.0002282355,0.0002232831,0.00005763932,0.0003364395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2115521,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1075734287613594,"score_gpt":0.4265432867614218,"score_spread":0.3189698580000624,"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."}}