{"id":"W4407730543","doi":"10.46690/elder.2024.04.01","title":"Capturing fine-grained teacher performance from student evaluation of teaching via ChatGPT","year":2024,"lang":"en","type":"article","venue":"Education and lifelong development research.","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Beijing Normal University; Crohn's and Colitis Foundation of America","keywords":"Mathematics education; Computer science; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001269282,0.0009823884,0.0005067748,0.001395818,0.0002827643,0.0008720987,0.0007126531,0.0006131638,0.002196772],"category_scores_gemma":[0.009519476,0.0001431954,0.0002683442,0.0009075826,0.0002794511,0.001084219,0.001474713,0.0008574916,0.001798056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004344168,"about_ca_system_score_gemma":0.0003660177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001801381,"about_ca_topic_score_gemma":0.005932067,"domain_scores_codex":[0.9987349,0.0004277051,0.00008405715,0.0002945913,0.000370341,0.00008833848],"domain_scores_gemma":[0.9943376,0.002418061,0.0007346346,0.0006303115,0.001358512,0.000520775],"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":[0.001625883,0.0008984859,0.2095111,0.001477727,0.0002529504,0.0009937516,0.004947032,0.01106644,0.04878239,0.001215848,0.02723514,0.6919932],"study_design_scores_gemma":[0.0001020938,0.002432615,0.632803,0.0003724247,0.0002695318,0.001389626,0.006283903,0.2546936,0.06615806,0.005699867,0.02949777,0.0002975934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8981847,0.0008101002,0.07504486,0.0003806133,0.0003051017,0.0003361891,0.009755439,0.005515133,0.009667898],"genre_scores_gemma":[0.9577973,0.000188681,0.02948974,0.0001192214,0.00007926889,0.0002588957,0.006466259,0.0001701648,0.005430595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002196772,"threshold_uncertainty_score":0.007348895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05858031486306325,"score_gpt":0.4098003805682974,"score_spread":0.3512200657052341,"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."}}