{"id":"W1077753102","doi":"10.1007/s40692-015-0040-3","title":"Mining learner–system interaction data: implications for modeling learner behaviors and improving overlay models","year":2015,"lang":"en","type":"article","venue":"Journal of Computers in Education","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Leverage (statistics); Formative assessment; TRACE (psycholinguistics); Overlay; Relation (database); Artificial intelligence; Data science; Machine learning; Human–computer interaction; Data mining; Mathematics education; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005614627,0.0009439074,0.00114265,0.003077082,0.0009053197,0.002769256,0.001640701,0.001145948,0.001097582],"category_scores_gemma":[0.05013113,0.0004921342,0.00105845,0.002868419,0.0004940826,0.006732721,0.0020848,0.002124812,0.0005413913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008953226,"about_ca_system_score_gemma":0.002060154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01075489,"about_ca_topic_score_gemma":0.01504141,"domain_scores_codex":[0.9961314,0.001699812,0.0005059785,0.0007115292,0.0007788943,0.0001723227],"domain_scores_gemma":[0.9603378,0.02912419,0.001954758,0.004899459,0.003128609,0.0005551479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006249267,0.001474434,0.5293003,0.0005949266,0.0007959059,0.0003081132,0.003063852,0.2234861,0.007359785,0.005697676,0.003640115,0.2236539],"study_design_scores_gemma":[0.00001461132,0.0001158292,0.02355485,0.00004074617,0.0001249672,0.000084231,0.0006755512,0.9581515,0.003098194,0.01273947,0.001366826,0.00003329166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5745501,0.0004064737,0.415113,0.001366494,0.00006673043,0.0003148367,0.004293824,0.002289636,0.001599029],"genre_scores_gemma":[0.9184752,0.0001833185,0.07730753,0.00005715381,0.0000297835,0.0001621815,0.003355679,0.00008400138,0.0003451716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01075489,"threshold_uncertainty_score":0.02969331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173710719988869,"score_gpt":0.3497566856162381,"score_spread":0.2323856136173512,"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."}}