{"id":"W4390686563","doi":"10.1016/j.nlp.2023.100052","title":"Deep temporal modelling of clinical depression through social media text","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Mental Health via Writing","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Computer science; Timeline; Social media; Artificial intelligence; Classifier (UML); Machine learning; Depression (economics); Data mining; Statistics; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001431441,0.000198895,0.0004215282,0.0001304944,0.0003468165,0.0001437345,0.0002873167,0.0002999418,0.0005528503],"category_scores_gemma":[0.0001674333,0.0001526882,0.000220747,0.0003083501,0.0001224046,0.0004522777,0.00006381647,0.00206288,0.00004995496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007159002,"about_ca_system_score_gemma":0.0001812645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003519984,"about_ca_topic_score_gemma":0.00001249165,"domain_scores_codex":[0.9971675,0.0002826591,0.001167837,0.0003594255,0.0005381315,0.0004844415],"domain_scores_gemma":[0.9987576,0.0004171924,0.0004448983,0.0001141895,0.0001296801,0.0001364338],"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":[0.0002409965,0.0001060357,0.002267184,0.0004478713,0.00005575615,0.0005556343,0.04420907,0.00003668706,0.000222135,0.0002139358,0.0010718,0.9505729],"study_design_scores_gemma":[0.01108814,0.0006010671,0.01684938,0.01382801,0.0007914315,0.01145744,0.1414027,0.7789595,0.002566943,0.01079828,0.008633553,0.003023569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6894258,0.2631169,0.03117155,0.0005110704,0.006667485,0.0001825018,0.000009960711,0.0002217119,0.008693063],"genre_scores_gemma":[0.9796912,0.00004548838,0.01600863,0.0002237192,0.003713658,0.000004310828,0.00001463591,0.000049251,0.0002490884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9475493,"threshold_uncertainty_score":0.8962304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007322898652962,"score_gpt":0.4643236625793267,"score_spread":0.3635913727140305,"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."}}