{"id":"W4399336118","doi":"10.1007/s12528-024-09404-6","title":"Using text mining and machine learning to predict reasoning activities from think-aloud transcripts in computer assisted learning","year":2024,"lang":"en","type":"article","venue":"Journal of Computing in Higher Education","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Think aloud protocol; Coding (social sciences); Affordance; Computer science; Protocol analysis; Natural language processing; Artificial intelligence; Psychology; Human–computer interaction; Usability; Cognitive science","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":[0.002014867,0.0005520663,0.000320052,0.002175766,0.0004826139,0.00133327,0.000589101,0.0008440989,0.001357172],"category_scores_gemma":[0.02013982,0.0001972356,0.0003322544,0.001311394,0.0003481736,0.001482608,0.0005173173,0.0008404564,0.000959623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004724026,"about_ca_system_score_gemma":0.0008380728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002654242,"about_ca_topic_score_gemma":0.004405259,"domain_scores_codex":[0.9976701,0.001186027,0.0002482138,0.0004299886,0.0003707182,0.00009492636],"domain_scores_gemma":[0.9679956,0.02728273,0.001564557,0.0004505724,0.002317483,0.0003891377],"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":[0.002672981,0.002855584,0.1910744,0.001492804,0.0003159533,0.001500399,0.02604441,0.006843417,0.08105288,0.001567382,0.007700237,0.6768795],"study_design_scores_gemma":[0.0003919297,0.002869491,0.4503341,0.000779585,0.0006988169,0.0023889,0.03644807,0.3629253,0.110392,0.01556102,0.01683129,0.0003794835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9498106,0.0003698114,0.04363979,0.0003849095,0.0001150468,0.0003978174,0.002408648,0.0008269502,0.002046401],"genre_scores_gemma":[0.9479207,0.0002389118,0.04669208,0.00008173019,0.00005308424,0.0003425416,0.002807545,0.00007509998,0.001788341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002654242,"threshold_uncertainty_score":0.0106557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04898514004665845,"score_gpt":0.2987161317507466,"score_spread":0.2497309917040881,"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."}}