Estimating Grades from Students' Behaviors in Programming Exercises Using Deep Learning

Programming exercises are time-consuming activities for many students. Therefore, many classes provide meticulous support for students through teaching assistants (TAs). However, individual students' programming behaviors are quite different from each other's, even when they are solving the same problem. It can be hard for TAs to understand the unique features of each student's programming behavior. We have used data mining to analyze students' programming behaviors in order to identify their various features. The purpose of this study is to present such behavioral features to TAs to improve the effectiveness of the assistance they can provide. In order to grasp the timing of guidance, we estimated the grades from the history of programming behavior.