{"id":"W4405995766","doi":"10.1080/09540091.2024.2445249","title":"Towards enhanced assessment question classification: a study using machine learning, deep learning, and generative AI","year":2025,"lang":"en","type":"article","venue":"Connection Science","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Quest University Canada","funders":"","keywords":"Computer science; Artificial intelligence; Generative grammar; Machine learning; Deep learning","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":[0.007063384,0.001330484,0.0008684802,0.003553819,0.0005977383,0.003128398,0.001743678,0.00154462,0.002166283],"category_scores_gemma":[0.02652027,0.0002978596,0.0009890627,0.002507291,0.0005977671,0.005555568,0.001654824,0.003100575,0.001587607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002495692,"about_ca_system_score_gemma":0.001562172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007689583,"about_ca_topic_score_gemma":0.007135124,"domain_scores_codex":[0.9945391,0.003045262,0.0002879677,0.0009850862,0.0009326791,0.0002099272],"domain_scores_gemma":[0.9780113,0.015159,0.001112673,0.00187905,0.002962911,0.0008749541],"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":[0.001084591,0.001854292,0.1081752,0.001270776,0.00032921,0.0002591971,0.002125032,0.04579453,0.006914102,0.007867143,0.01191795,0.812408],"study_design_scores_gemma":[0.0001079979,0.0007717956,0.03919765,0.0002371079,0.0001800223,0.0003122148,0.001580129,0.9133257,0.01265435,0.01221683,0.01931252,0.0001036386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.786058,0.009289071,0.1747204,0.003197414,0.0005169555,0.0009051981,0.002154127,0.003990334,0.01916851],"genre_scores_gemma":[0.9352661,0.0008720702,0.05609587,0.0003908371,0.0001400598,0.00018107,0.002924843,0.00009556507,0.004033625],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007689583,"threshold_uncertainty_score":0.03735524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.041588579686941,"score_gpt":0.378155095744837,"score_spread":0.3365665160578959,"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."}}