{"id":"W4409526936","doi":"10.5430/wjel.v15n5p272","title":"Optimizing Automated Essay Scoring: A Comparative Study of Machine Learning Approaches with a Focus on Ensemble Methods","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Focus (optics); Computer science; Ensemble learning; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.0106926,0.001314298,0.001435811,0.001600117,0.0003959241,0.001536599,0.001240143,0.001143145,0.0006233429],"category_scores_gemma":[0.02707485,0.0004158898,0.0007042193,0.001463457,0.0004393319,0.001818562,0.001350965,0.001556756,0.0002811953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000842497,"about_ca_system_score_gemma":0.001087478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003227503,"about_ca_topic_score_gemma":0.003170123,"domain_scores_codex":[0.9935064,0.00392413,0.0004257672,0.000713875,0.001205873,0.0002238914],"domain_scores_gemma":[0.9754502,0.01845193,0.0009604328,0.001555881,0.003243841,0.0003377934],"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":[0.0003197484,0.0002238603,0.01174231,0.0002294715,0.0003481229,0.00004377853,0.0002677425,0.4895414,0.00148484,0.002472142,0.001413419,0.4919132],"study_design_scores_gemma":[0.00001426471,0.0002620943,0.003057203,0.0000353729,0.0000444071,0.00002674358,0.00007879845,0.9924591,0.001293486,0.001683748,0.001026692,0.00001811319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3186437,0.008582069,0.66199,0.001272551,0.0002198017,0.0002500116,0.0001658913,0.001694385,0.007181629],"genre_scores_gemma":[0.8606071,0.001469739,0.1353587,0.000181748,0.0001411865,0.0001474665,0.0003143471,0.0001474691,0.001632295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0106926,"threshold_uncertainty_score":0.05654854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04555861244710417,"score_gpt":0.3266675701460139,"score_spread":0.2811089576989097,"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."}}