Optimizing Automated Essay Scoring: A Comparative Study of Machine Learning Approaches with a Focus on Ensemble Methods

Abstract

This study examines the optimization of Automated Essay Scoring (AES) systems for English language writing using advanced machine learning techniques, focusing on ensemble methods to enhance accuracy, consistency, and interpretability. An English written corpus includes a total of 17,793 English essays: 12,976 from the Automated Student Assessment Prize (ASAP) dataset and 4,817 from the Khon Kaen University Academic English Language Test (KKU-AELT). Linguistic features and semantic content critical to English writing proficiency were assessed using BERT, XGBoost, and Neural Networks models. Combining these models with Ridge Regression, the ensemble approach substantially reduced Root Mean Squared Error (RMSE) while balancing Cohen's Kappa and Quadratic Weighted Kappa scores, highlighting interpretive alignment challenges. The SHAP values were employed for feature importance analysis, and Bayesian optimization was applied for hyperparameter tuning, enhancing model transparency. The findings highlight the potential of ensemble AES to evaluate diverse aspects of English such as argumentation, coherence, and vocabulary complexity—applicable to various domains, from applied linguistics to literature and translation studies. The research offers scalable solutions for teaching and assessment, aligning AES systems with the pedagogical goals of supporting skill acquisition and providing actionable feedback. The study concludes that advanced AES models can serve as valuable complementary tools in language assessment, assisting teachers by providing consistent, detailed insights that foster English writing proficiency and skills development across diverse educational contexts.