Simulation Results of a Spatio-Temporal Perplexion Estimation Method Based on Learners' Facial Expression Changes

In recent years, the field of I'CT education has emerged, and the research and development of educational support robots has attracted significant interest. In this study, we focus on a perplexity estimation method for educational support robots that estimates perplexity based on learners' facial expressions. The conventional method for estimating perplexion from facial expressions at a given time is not yet sufficiently accurate. It is believed that the accuracy of the method can be improved by using not only facial expressions at a given time but also time-series data on changes in facial expressions between that time and the previous time. This study focuses on a perplexion estimation method for educational support robots that estimates perplexion based on the facial expressions of learners. The objective of this study is to verify the accuracy of the spatio-temporal perplexion estimation method through simulation experiments.