Data Mining of Students’ Behaviors in Programming Exercises

Abstract

Programming exercises are time-consuming activities for many students. Therefore, most classes provide meticulous supports for students by employing teaching assistants (TAs). However, the programming behaviors of a particular student are quite different from other students’ behavior, even though they are solving the same problem. It is hard for TAs to understand the detailed features of each student’s programming behavior. We have performed data mining over the records of students’ programming behaviors in order to elicit the detailed features of each student’s programming behavior. The purpose of this study is to present the elicited such features for TAs so that they can provide effective assistances. We have performed data mining over the chronological records of the compilation and execution of individual students. As a result, we have found that there is a correlation between the programming activities and the duration time for problem solving. Based on the data mining, we have provided TAs some guidelines for each particular group of students. We have confirmed that our classifications and guidelines are reasonable through experiments over programming exercises. We have observed students who received appropriate guidance based on our data mining improved their programming performances.