S7-COMP11-1 - Evaluation of students programming skills on a computer programming course with a hierarchical clustering algorithm

3. Research Full Paper
Davi Silva¹ , Carlos Silla^1
1 Pontificia Universidade Catolica do Parana

Introduction
This Research Full Paper presents a computational hierarchical clustering approach to grouping college students from a CS1 course according to their programming skills.
Context: Although computer courses have become popular, the lessons related to computer programming still pose several challenges for beginners. Throughout the course, determination and empathy for content lead students to different levels of knowledge. Therefore, it is necessary to have teaching strategies to make learning more engaging and focused on the specific difficulties of students. It would be interesting to segment students into groups according to their skills so that the teacher can direct learning and adopt a more appropriate pedagogical strategy for each student. Objective: In this paper, we present a computational approach to identify groups of students in a CS1 course that need extra help with the programming content. Method: In this CS Education Research Paper, we first defined a set of features that characterize the student’s programming skills in a CS1 course. Next, we applied a hierarchical clustering algorithm to bring together the students with similar skills by analyzing the source code they developed for different tasks. Finally, we evaluated the quality of the model and analyzed the different clusters. Results: We processed a total of 630 source code tasks, for which our results indicate the formation of three clusters. We have found that one of the clusters has a large number of students with possible difficulties in programming. The other two clusters, although having different coding behaviors, reached high levels of knowledge about the contents taught. Conclusion: We conclude that features extracted from the students source codes can be used to group students into clusters that indicate their performance trends throughout the course.