{"id":"W2157019309","doi":"","title":"Using Feature Selection and Unsupervised Clustering to Identify Affective Expressions in Educational Games","year":2006,"lang":"en","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Cluster analysis; Educational game; Feature selection; Unsupervised learning; Affective computing; Selection (genetic algorithm); Machine learning; Artificial intelligence; Affect (linguistics); Feature (linguistics); Game based learning; Multimedia; Psychology","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":[0.00007168992,0.00006973514,0.00006816843,0.0001931833,0.00007367978,0.00002700157,0.00002322251,0.00008033933,0.0009102938],"category_scores_gemma":[0.00001423482,0.00006695453,0.00001808799,0.0001951219,0.000009792354,0.00008947024,0.00001718092,0.00009208117,0.00003445924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004463003,"about_ca_system_score_gemma":0.00001407871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005296859,"about_ca_topic_score_gemma":0.001602833,"domain_scores_codex":[0.9994602,0.00007714898,0.00008899829,0.0001965428,0.00005558024,0.0001214965],"domain_scores_gemma":[0.9998077,0.00004568664,0.00002091609,0.00004978414,0.0000374804,0.00003845081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002389917,0.001160113,0.1183655,0.0000717215,0.00006381769,0.000007756362,0.007851169,0.001642486,0.7957324,0.00749139,0.02930236,0.03807227],"study_design_scores_gemma":[0.000595903,0.00002897231,0.9941396,0.00006725696,0.000008723036,0.00004248333,0.000915003,0.0007013768,0.001864807,0.001111166,0.0003995762,0.0001251053],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9727253,0.00004789442,0.008290886,0.0007623833,0.0003684831,0.0002270039,0.000003594017,0.00003348865,0.01754102],"genre_scores_gemma":[0.9919782,0.000001383262,0.003583633,0.0001990439,0.000164559,0.00003013439,0.00001362394,0.000009064706,0.004020343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8757741,"threshold_uncertainty_score":0.9967079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04060204550777052,"score_gpt":0.3785357159724726,"score_spread":0.3379336704647021,"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."}}