An Emotion Transition Model using Fuzzy Inference

Abstract

This paper proposes an emotion transition model considering internal emotion and external input. The proposed model has internal emotion values representing each intensity of multiple emotions as internal states. Each intensity of emotions estimated from the input texts is given as the external input. These values of intensity are used as antecedent part, and emotion transition is estimated by fuzzy inference. The proposed model can treat the same external inputs differently considering the internal states: It can express emotion transition more naturally. According to subjective evaluation experiments, high correlation between the proposed model and humans was obtained.