Leveraging Targeted Regions of Interest by Analyzing Code Comprehension With AI-Enabled Eye-Tracking
Term of Award
Master of Science, Computer Science (M.S.C.S.)
Document Type and Release Option
Thesis (open access)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department of Computer Science
Andrew A. Allen
Committee Member 1
Committee Member 2
Code comprehension studies techniques for extracting information that give insights on how code is understood. For educators teaching programming courses, this is an important but often difficult task, especially given the challenges of large class sizes, limited time, and grading resources. By analyzing where a student looks during a code comprehension task, instructors can gain insights into what information the student deems important and assess whether they are looking in the right areas of the code. The proportion of time spent viewing a part of the code is also a useful indicator of the student's decision-making process. The goal of this research is to analyze the differences in how students' eyes traverse across code during coding comprehension activities and to offer a systematic way for distinguishing students with a solid understanding of the exercise from those who require further assistance. The study uses coding exercises seeded with errors, measured fixation counts, and average fixation durations of the students' eyes within targeted regions of interest (TROI) using an AI-Enabled Eye-Tracking System (NiCATS). The results of the study showed that students' grades (as a proxy for understanding of the code's context and their decision-making skills) were positively correlated with a higher ratio of the number of fixations in the TROI.
Hossain, Md Shakil, "Leveraging Targeted Regions of Interest by Analyzing Code Comprehension With AI-Enabled Eye-Tracking" (2023). Electronic Theses and Dissertations. 2548.
Research Data and Supplementary Material