{"id":"W4390014769","doi":"10.3390/ecsa-10-16009","title":"Optimizable Ensemble Regression for Arousal and Valence Predictions from Visual Features","year":2023,"lang":"en","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Outaouais","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Valence (chemistry); Arousal; Computer science; Concordance correlation coefficient; Artificial intelligence; Correlation; Mean squared error; Regression; Correlation coefficient; Pearson product-moment correlation coefficient; Machine learning; Speech recognition; Pattern recognition (psychology); Statistics; Mathematics; Psychology; Chemistry","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":[0.00008778996,0.00007608306,0.00008392082,0.00007955614,0.0001451928,0.00002291687,0.0000373595,0.0001122687,0.0007680261],"category_scores_gemma":[0.00002742436,0.00006115513,0.0000345455,0.0001102954,0.00002781407,0.00006474274,0.00002270357,0.00007291554,0.0001989543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006348464,"about_ca_system_score_gemma":0.000008207378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087221,"about_ca_topic_score_gemma":0.00003739568,"domain_scores_codex":[0.9993961,0.00003477689,0.00009962657,0.000238071,0.00006623651,0.0001651869],"domain_scores_gemma":[0.9996231,0.0001509689,0.00003105503,0.00009559725,0.00003598916,0.00006335627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002531817,0.000232088,0.001353662,0.00002649995,0.00009992596,0.00001089633,0.00191007,0.0000855943,0.006334345,0.003420309,0.9337237,0.05254975],"study_design_scores_gemma":[0.0232873,0.00447676,0.5224156,0.0009551157,0.0007356748,0.000294025,0.02695403,0.0761738,0.0364779,0.05850446,0.2470957,0.002629617],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7763525,0.0005339889,0.08077876,0.003203779,0.005137668,0.00122104,0.000432211,0.001786626,0.1305535],"genre_scores_gemma":[0.8161215,0.0002584427,0.007556367,0.000607129,0.0005469489,0.0002371792,0.0007422973,0.00003733047,0.1738928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.686628,"threshold_uncertainty_score":0.8409348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822647717683943,"score_gpt":0.3573377319782658,"score_spread":0.3191112548014264,"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."}}