Classification of Students’ Mathematical Answers Using BART-Based Machine Learning

Using machine learning (ML) for automated grading is a big step toward effective and reliable assessment in today’s educational environment. This work aims to use ML to evaluate student answers to various questions, such as simultaneous equations, word problems, and quadratic equations. Our method attempts to reliably classify answers as correct, partially correct, and incorrect by imitating expert-level grading. This research explores the use of BART embeddings using the application of Stacking Classifiers. XGBoost as a meta-classifier has exhibited the best accuracy of $97.89 \%$ mean accuracy with standard deviation of 0.02. The results demonstrate the potential of machine learning techniques to revolutionize the grading process, ensuring consistency and efficiency in educational assessments.