{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001526269,0.0001257728,0.0001397113,0.0003169206,0.001034072,0.0005430522,0.0004011063,0.0000393997,0.00001008854],"category_scores_gemma":[0.0003548007,0.000121734,0.00002117617,0.001253281,0.0001614884,0.0008840653,0.0003005954,0.0003094824,0.000002772638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002690174,"about_ca_system_score_gemma":0.00034365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000126193,"about_ca_topic_score_gemma":0.00006163196,"domain_scores_codex":[0.9981341,0.0002673301,0.0002217711,0.0007466121,0.0004110298,0.0002191568],"domain_scores_gemma":[0.9990857,0.00005584081,0.0001339451,0.0002781753,0.0003720815,0.00007426331],"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":[0.00001555034,0.0003409715,0.1083414,0.00003117918,0.00004164594,0.000006567042,0.008470469,0.04387494,0.2331394,0.22672,0.000011531,0.3790064],"study_design_scores_gemma":[0.0002707217,0.0001374418,0.0191858,0.00001741079,0.000007727737,0.000005507515,0.0006544437,0.9733596,0.004915063,0.0008286993,0.0004939466,0.0001236403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2816355,0.0000730481,0.7158108,0.0006580765,0.0004358972,0.0002015503,6.957239e-8,0.0001314326,0.001053563],"genre_scores_gemma":[0.9642012,0.0000173256,0.03504556,0.0001530865,0.00003620494,0.00002806717,5.154658e-7,0.000003471269,0.0005145819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9294847,"threshold_uncertainty_score":0.7953353,"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."}}