{"id":"W7126391127","doi":"10.18653/v1/2024.clpsych-1.8","title":"Explainable Depression Detection Using Large Language Models on Social Media Data","year":2024,"lang":"","type":"article","venue":"","topic":"Mental Health via Writing","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social media; Depression (economics); Language model; Data collection; Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001767934,0.0003643038,0.0003629387,0.0003213502,0.0008947079,0.0002092574,0.0005316422,0.0005251706,0.004845353],"category_scores_gemma":[0.00009023898,0.0003679434,0.00008736588,0.0004963321,0.00005005592,0.0007376341,0.0006754517,0.0009193752,0.0009373208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004513887,"about_ca_system_score_gemma":0.0001392702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000893536,"about_ca_topic_score_gemma":0.00062226,"domain_scores_codex":[0.9956563,0.0005663463,0.0007102446,0.001368312,0.0005375802,0.001161245],"domain_scores_gemma":[0.9980456,0.0005811027,0.0001311512,0.0009874363,0.00003086829,0.000223824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001219785,0.001018978,0.00008471429,0.003719993,0.000264198,0.001168371,0.09833464,0.0001545335,0.01749739,0.02115974,0.01603738,0.8393403],"study_design_scores_gemma":[0.001676362,0.00009756095,0.0001085257,0.001070238,0.0001503683,0.0001158096,0.05378401,0.9292378,0.005953181,0.001050046,0.006145607,0.0006104775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8459438,0.01363332,0.04659455,0.0003349372,0.01885237,0.00124408,0.0009689958,0.000700357,0.07172757],"genre_scores_gemma":[0.9941152,0.00008056089,0.0004280604,0.0004325174,0.002631358,0.0000259064,0.0002463089,0.0001187648,0.001921379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9290833,"threshold_uncertainty_score":0.9998773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.196775648756316,"score_gpt":0.4544282189852733,"score_spread":0.2576525702289573,"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."}}