{"id":"W2779582454","doi":"10.1109/taffc.2017.2784832","title":"Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":266,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Research Resources; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Samsung; NEC Corporation; National Institutes of Health; National Heart, Lung, and Blood Institute","keywords":"Machine learning; Artificial intelligence; Multi-task learning; Computer science; Mood; Leverage (statistics); Feature engineering; Context (archaeology); Deep learning; Task (project management); Psychology; Engineering; Clinical psychology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005075571,0.0001791106,0.0002421562,0.0001159705,0.002217363,0.000108902,0.0001014989,0.0001011533,0.00007064025],"category_scores_gemma":[0.00004178267,0.0001893821,0.0001252555,0.00004511545,0.0001164459,0.0001213642,0.000002828389,0.0004041867,0.00002007203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007949158,"about_ca_system_score_gemma":0.00002718408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002658837,"about_ca_topic_score_gemma":0.0002246016,"domain_scores_codex":[0.998716,0.0001967134,0.0002035997,0.0004384176,0.0001094017,0.0003358633],"domain_scores_gemma":[0.9989625,0.0003571808,0.0002698701,0.0001983901,0.00009290812,0.0001192054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003069628,0.0006332396,0.01115248,0.0002573788,0.0004025332,0.000005309734,0.0116563,0.003803636,0.0004880663,0.00051232,0.0001919865,0.9705898],"study_design_scores_gemma":[0.04291981,0.008068107,0.5344936,0.004327931,0.0006043417,0.0002761451,0.03258037,0.354636,0.01695882,0.00079698,0.001617829,0.002720031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2521655,0.00006996047,0.7425392,0.000490748,0.00156563,0.0007519137,0.0000380099,0.0002024707,0.002176578],"genre_scores_gemma":[0.997588,0.00001573889,0.001368272,0.0001326651,0.0001839735,0.00005393403,0.000008774019,0.00003512522,0.0006134813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9678698,"threshold_uncertainty_score":0.9990816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05221817964537573,"score_gpt":0.3651353464191073,"score_spread":0.3129171667737316,"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."}}