Estimating Learner’s Perspective in Programming: Analysis of Operation Time Series in Code Puzzles
Hiroki Ito, Hiromitsu Shimakawa, Fumiko Harada · 2021 16th International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · 2021
In programming education, the instructor tries to find out the learner who needs help by grasping the understanding using a written test and e-learning. However, in reality, not many learners will acquire the skill of writing source codes. This kind of situation implies that programming ability of learners cannot be measured only by knowledge tests or the data obtained from answer results. This paper discusses understanding analysis that focuses on the thought process of programming. The study analyses time series of operations of learners struggling with a code puzzle, where they arrange code fragments. The proposed method aims to estimate their perspectives on how fragments are organized to achieve given requirements. As a result of the experiment, we were able to represent the learner’s perspective as a hidden state of the hidden Markov model.