Digital Essay Assessment using Machine Learning Algorithms

Essay are considered as the most prominent way in assessing the student performance. Manual grading of the essay are considered to be a hectic tasks for both students and instructors due to various reasons such as time consuming, prone to subjectivity, inconsistencies and lack of reliability may be influenced by biases, such as prior knowledge of the student or their back ground. The solution to all these problems has been rectified by using Automated Essay Scoring (AES) system. This technical paper proposes a novel AES system that utilizes various Machine Learning (ML) algorithms such as Linear Regression, Lasso Regression, Ridge Regression, Gradient Boosting Regression, Bayesian Regression, Elastic Net Regression, Random Forest Regression, Decision Tree Regression, Gaussian Process Regression, Support Vector Regression, Polynomial Regression, XG Boost regression and XGBoost with Polynomial Features and discovered that XGBoost with Polynomial features achieved the best results with an average Quadratic Weighted Kappa (QWK) value of 0.68.