{"id":"W2905178934","doi":"10.1109/taffc.2018.2885744","title":"Using Circular Models to Improve Music Emotion Recognition","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Categorical variable; Computer science; Valence (chemistry); Affect (linguistics); Artificial intelligence; Affective computing; Arousal; Regression; Natural language processing; Pattern recognition (psychology); Machine learning; Mathematics; Psychology; Statistics; Communication","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0003817892,0.0002256026,0.0002046025,0.0003150359,0.0008022339,0.0002137997,0.0003109225,0.00009196393,0.00001765892],"category_scores_gemma":[0.000008930426,0.0002424799,0.0001174233,0.0008696226,0.00006062899,0.0007459647,0.000009981844,0.0002517498,0.0001132866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002244578,"about_ca_system_score_gemma":0.00007393677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004768696,"about_ca_topic_score_gemma":0.000009043709,"domain_scores_codex":[0.9982499,0.0001371894,0.0002398102,0.0006979542,0.0002780526,0.0003970577],"domain_scores_gemma":[0.9989738,0.0001048024,0.0001184827,0.0003555549,0.0003089355,0.000138433],"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":[0.0000158797,0.0001379582,0.000001991945,0.00003552102,0.0000402886,0.00000526606,0.003754575,0.06308798,0.07757997,0.0001091774,0.0000401766,0.8551912],"study_design_scores_gemma":[0.0003214215,0.0002470014,0.00004642199,0.000207501,0.00002092076,0.00002482752,0.00005852939,0.8612899,0.1350035,0.002460915,0.0000181235,0.0003009828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2175618,0.00000586943,0.7795669,0.00009180453,0.001493191,0.0002997637,0.000003022133,0.0002803943,0.000697209],"genre_scores_gemma":[0.916408,5.981915e-7,0.08207592,0.001162565,0.0003075938,0.000007987313,5.390337e-7,0.00002237275,0.00001442274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8548902,"threshold_uncertainty_score":0.9888045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07868070166492959,"score_gpt":0.2848457243521875,"score_spread":0.2061650226872579,"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."}}