{"id":"W3047346431","doi":"10.2196/17818","title":"Using Machine Learning and Smartphone and Smartwatch Data to Detect Emotional States and Transitions: Exploratory Study","year":2020,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Wearable computer; Context (archaeology); Artificial intelligence; Psychology; Computer science; Smartwatch; Cognitive psychology; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002682964,0.0005694592,0.0005639252,0.001303123,0.0004044607,0.0007525395,0.0007099214,0.0007630105,0.0007066854],"category_scores_gemma":[0.007939256,0.0002882185,0.0009999964,0.001320054,0.0004162069,0.000806695,0.0007105928,0.0006538579,0.0004728339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003165591,"about_ca_system_score_gemma":0.0003776642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004830542,"about_ca_topic_score_gemma":0.005719458,"domain_scores_codex":[0.99768,0.001255839,0.0001454927,0.000462164,0.0002681967,0.0001883657],"domain_scores_gemma":[0.9926763,0.005023404,0.0007108772,0.0006843804,0.0006734161,0.0002316549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006607804,0.004609716,0.8828178,0.0004351522,0.0004196032,0.000686571,0.003782323,0.007013113,0.004828284,0.000303548,0.001671334,0.09277172],"study_design_scores_gemma":[0.00006859776,0.00198826,0.8949524,0.0001147689,0.0002441322,0.0007407612,0.005790603,0.08871977,0.003564159,0.0007160297,0.003015436,0.00008511919],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946391,0.00009274874,0.004081391,0.00004715044,0.000007687817,0.0001394608,0.0006575393,0.00003130006,0.0003037037],"genre_scores_gemma":[0.9877616,0.0000829956,0.009919945,0.00004725426,0.000018175,0.0002209635,0.001689821,0.00001218466,0.0002471329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004830542,"threshold_uncertainty_score":0.01418906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2168384361872594,"score_gpt":0.4314461148764102,"score_spread":0.2146076786891508,"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."}}