Examining the Effect of Machine-Learning Programming Simulator on Student Performance and Student Anxiety

Acquiring programming skills can be a complex and daunting challenge for novice university students. Mastering the syntax of programming languages is not just a superficial endeavor; it requires students to develop a robust set of principles to tackle specific problem scenarios. Machine learning technology has the potential to be beneficial across various industries; however, its application in educational tools remains inadequate. Therefore, this project aims to implement machine learning technology in a simulator designed to assist students in evaluating their programming courses. This study developed a machine-learning programming simulator and explored its impact on students with varying levels of anxiety. Educational Data Mining (EDM) refers to the application of data mining techniques to extract valuable information and insights from extensive data repositories within the education sector. The primary goal of this approach is to evaluate student performance in programming courses. To assess the effects of technology on academic performance, the study employed Analysis of Variance (ANOVA) and Analysis of Covariance (ANCOVA) methodologies. The findings suggest that both students with high levels of anxiety and those with low levels of anxiety benefit from exposure to machine learning technology. By utilizing a machine learning programming simulator, students’ performance in programming courses can significantly improve, irrespective of their anxiety levels.