{"id":"W4380355000","doi":"10.1007/s11760-023-02578-z","title":"Detecting disengagement in virtual learning as an anomaly using temporal convolutional network autoencoder","year":2023,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network","funders":"","keywords":"Autoencoder; Disengagement theory; Binary classification; Computer science; Anomaly detection; Artificial intelligence; Convolutional neural network; Machine learning; Support vector machine; Class (philosophy); Deep learning; Pattern recognition (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":[0.001404017,0.0001784581,0.0001991714,0.000212156,0.0007269002,0.0004840672,0.0002478073,0.00006297927,0.000008974089],"category_scores_gemma":[0.0001387486,0.0001788546,0.00004041012,0.0009699186,0.0000773209,0.00130823,0.0002572513,0.0005053256,0.00001539164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004529462,"about_ca_system_score_gemma":0.0002008112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009183159,"about_ca_topic_score_gemma":0.00001715206,"domain_scores_codex":[0.9981521,0.000247969,0.000311127,0.0004950375,0.0002916043,0.0005021916],"domain_scores_gemma":[0.9993928,0.0001362965,0.0001439788,0.0001215242,0.00008369383,0.000121702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004714663,0.0001356159,0.1273713,0.0001796615,0.00003886761,0.0005489258,0.005228252,0.5653786,0.01386638,0.001438698,0.0001023741,0.2856641],"study_design_scores_gemma":[0.000285658,0.0001210345,0.004590423,0.000189157,0.000009829197,0.00002037184,0.0007386312,0.9902513,0.0001281962,0.003333233,0.00009490155,0.0002372545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5498841,0.0001700524,0.4490112,0.0003833898,0.00006656538,0.00006535911,6.81066e-7,0.0003212154,0.00009738625],"genre_scores_gemma":[0.9656038,0.000006269039,0.03369651,0.0001575081,0.0002713912,0.000003543966,0.000007805796,0.00001928686,0.000233838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4248727,"threshold_uncertainty_score":0.7293479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02444536672046931,"score_gpt":0.3077846753515801,"score_spread":0.2833393086311108,"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."}}