{"id":"W3038090822","doi":"10.1016/j.chb.2020.106457","title":"Construct and consequential validity for learning analytics based on trace data","year":2020,"lang":"en","type":"article","venue":"Computers in Human Behavior","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"TRACE (psycholinguistics); Learning analytics; Analytics; Data science; Construct (python library); Computer science; Data analysis; Set (abstract data type); Reliability (semiconductor); Construct validity; Validity; Psychology; Data mining; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.08316315,0.001204762,0.001365721,0.006708256,0.002244611,0.004383125,0.002225122,0.002466344,0.002235561],"category_scores_gemma":[0.4390529,0.0008719807,0.004168668,0.003304677,0.00889931,0.007609881,0.005595404,0.004687545,0.0003551934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002347381,"about_ca_system_score_gemma":0.005076624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002735654,"about_ca_topic_score_gemma":0.002278347,"domain_scores_codex":[0.9310287,0.03275073,0.006074419,0.009975333,0.0185902,0.001580646],"domain_scores_gemma":[0.3187714,0.5782436,0.0220209,0.04098892,0.03736397,0.002611223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001940846,0.001526747,0.7095975,0.0009981107,0.002659644,0.0001893332,0.005807954,0.03452012,0.002005375,0.1393406,0.001614356,0.09979936],"study_design_scores_gemma":[0.0005072679,0.001469914,0.1938247,0.0007867772,0.001300157,0.0005082909,0.003060615,0.2861178,0.006376157,0.5021484,0.003704683,0.0001951757],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6096066,0.00076505,0.3682595,0.001834233,0.0002611614,0.001300862,0.00137675,0.0004476943,0.01614811],"genre_scores_gemma":[0.9672163,0.0001149755,0.03068535,0.00009375108,0.00008363894,0.0005956059,0.0008348933,0.00005591233,0.0003195656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08316315,"threshold_uncertainty_score":0.439814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1571785384843767,"score_gpt":0.3558847405011091,"score_spread":0.1987062020167324,"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."}}