Classifying Solving Behavior by Handwriting on Tablets
Ryosuke Goshima, Fumiko Harada, Hiromitsu Shimakawa · 2021
In this thesis, we propose a method to estimate the learner's solving behavior during the question exercises from the handwriting situation on the tablet. The model of random forest is constructed to estimate the solving behavior. The constructed model classifies exactly not only the state in which the hands are stopped and the state in which the hands are moving but also the state of answering correctly and the state of answering incorrectly.