Estimating Emotion for Each Personality by Analyzing BVP

Abstract

This research estimates emotions of university students from their BVP (blood volume pulse). Negative emotion of university students causes school dropout, which is becoming a serious problem in Japan. It is indispensable for school staffs and counselors to know when and where students have negative emotion in the campus. Since BVP signals along with emotion changes vary with personality types, we build a model dependent on personality type, to estimate student emotion from characteristics of blood volume signals. Experimental results show that the model for each personality type improves the accuracy of emotion estimation for new students. Positive or negative emotion estimated from BVP signals contributes to enhancement of campus environment by school counselors.