In-process Feedback by Detecting Deadlock based on EEG Data in Exercise of Learning by Problem-posing

Abstract

Giving feedback to learning activities is one of the most important issues so as to realize adaptive learning. Feedback for the product of the activity (we call it “after-process feedback”) has previously been implemented in many interactive and adaptive learning environments. However, feedback during the activity (we call it “in-process feedback”) has been hardly implemented. When a learner gets stuck or frustrated during some stage of the process, in-process feedback is much better than after-process feedback. The difficulty in realizing in-process feedback lies in the timing and content of the feedback. To solve this, we developed and implemented affect detection based on EEG data for deciding the timing of the feedback, and knowledge state estimation based on knowledge structure for the content of the feedback. Furthermore, in this study, we realize and evaluate the in-process feedback by detecting deadlocks based on EEG data for learning through problem-posing.