{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372508,0.0002143935,0.0003772481,0.0007871846,0.0001618632,0.0006340198,0.000304934,0.00009516512,0.00001003268],"category_scores_gemma":[0.0000808872,0.0002076974,0.00007929446,0.000656906,0.00001788028,0.0007241561,0.0001073309,0.000915568,0.000001669098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003242704,"about_ca_system_score_gemma":0.0002409501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003469077,"about_ca_topic_score_gemma":0.00001105158,"domain_scores_codex":[0.9977472,0.000477766,0.0007265445,0.0003708934,0.0003621942,0.0003153468],"domain_scores_gemma":[0.9987801,0.0005696709,0.0003244582,0.0001181109,0.00009983429,0.0001078318],"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":[0.00004623022,0.0001742811,0.1957971,0.0002147206,0.0001155476,0.0001546554,0.1562569,0.4464006,0.00711659,0.004189111,0.00006968243,0.1894647],"study_design_scores_gemma":[0.0003016914,0.0002240067,0.2323375,0.006957279,0.00001988887,0.0001734997,0.002027469,0.7537509,0.0001715917,0.00007334012,0.003649616,0.0003131952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7706243,0.001902348,0.2238905,0.0002323266,0.003097838,0.00008481264,2.415019e-7,0.00006357726,0.0001039834],"genre_scores_gemma":[0.9124454,0.00001390131,0.08606843,0.00006183593,0.00101456,6.127401e-7,0.000001465548,0.00002516327,0.0003686321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3073503,"threshold_uncertainty_score":0.8469654,"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."}}