{"id":"W3028133604","doi":"10.1016/j.ijinfomgt.2020.102141","title":"A big data analytics framework for detecting user-level depression from social networks","year":2020,"lang":"en","type":"article","venue":"International Journal of Information Management","topic":"Mental Health via Writing","field":"Psychology","cited_by":67,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Toronto Metropolitan University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; International Business Machines Corporation","keywords":"Big data; Feeling; Mood; Social network (sociolinguistics); Depression (economics); Mental health; Computer science; Psychology; Analytics; Social support; Process (computing); Data science; Internet privacy; Social media; World Wide Web; Social psychology; Data mining; Psychiatry","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":[0.0005779727,0.000109285,0.0001622764,0.0001767094,0.000113625,0.0001464731,0.000976244,0.00008667116,0.0001637937],"category_scores_gemma":[0.0002136082,0.0001071596,0.00008023943,0.0001353843,0.00001443742,0.0007657031,0.0003518117,0.0002828238,0.00004279946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000120068,"about_ca_system_score_gemma":0.00002106182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000189006,"about_ca_topic_score_gemma":0.000003377565,"domain_scores_codex":[0.998118,0.00004620757,0.0009961342,0.0001212151,0.0005358208,0.0001825956],"domain_scores_gemma":[0.9980873,0.0002273694,0.001136605,0.0001622323,0.0002864796,0.0001000184],"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":[0.000844055,0.00006052501,0.003787067,0.00006237013,0.0008077031,0.00002528527,0.003280773,0.002339786,0.000004336966,0.01119536,0.02144102,0.9561517],"study_design_scores_gemma":[0.01394553,0.0005320161,0.1379593,0.001319539,0.0005838599,0.00006825911,0.03585533,0.2581278,0.0001612071,0.01221146,0.5382365,0.0009992006],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007558604,0.0000582512,0.9845851,0.002548572,0.00312489,0.0002525513,0.0001607543,0.00002128232,0.001689976],"genre_scores_gemma":[0.9095877,0.00002219396,0.07834119,0.008062655,0.003696204,0.00001237185,0.0002418815,0.0000144685,0.00002129506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9551525,"threshold_uncertainty_score":0.4369842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1858974345952778,"score_gpt":0.4134478687290329,"score_spread":0.2275504341337551,"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."}}