{"id":"W3194233023","doi":"10.1007/s40692-021-00196-7","title":"Analyzing students’ performance in computerized formative assessments to optimize teachers’ test administration decisions using deep learning frameworks","year":2021,"lang":"en","type":"article","venue":"Journal of Computers in Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Test (biology); Cluster analysis; Computer science; Schedule; Psychology; Mathematics education; Artificial intelligence","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":[0.002078524,0.0006406735,0.00036473,0.001165143,0.0002044174,0.001146952,0.000625753,0.000511478,0.001009199],"category_scores_gemma":[0.01321258,0.0002104803,0.0002931193,0.0007172532,0.000182235,0.0009602216,0.0006160027,0.0009202662,0.0005289483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006597558,"about_ca_system_score_gemma":0.001244495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006408115,"about_ca_topic_score_gemma":0.01051452,"domain_scores_codex":[0.9986639,0.0004651361,0.000142531,0.0002212311,0.0003540028,0.00015316],"domain_scores_gemma":[0.9912317,0.004550666,0.001022617,0.0004676064,0.002326618,0.0004006938],"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":[0.0008977027,0.001769711,0.3270858,0.000131055,0.0001659926,0.0001716053,0.0009963365,0.07169526,0.01871999,0.001218124,0.004134074,0.5730143],"study_design_scores_gemma":[0.00004099005,0.0007153037,0.1343803,0.00006369245,0.00009456872,0.00007961169,0.0006615281,0.8315275,0.02778354,0.002388691,0.002207398,0.00005682184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9370745,0.0001216352,0.05931694,0.0002825432,0.00003188892,0.0000528085,0.0003431299,0.0007324392,0.002044038],"genre_scores_gemma":[0.9863768,0.00002623692,0.01257964,0.00002537132,0.000004586966,0.00001994124,0.0002492109,0.00002812316,0.000689961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006408115,"threshold_uncertainty_score":0.01274163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02118810291347887,"score_gpt":0.3760029940119179,"score_spread":0.3548148910984391,"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."}}