Emotional Intensity Evaluation Method Based on Galvanic Skin Response Signal

In this paper, we propose a method for evaluating the emotional intensity based on Galvanic Skin Response (GSR) signal in real-time. Firstly, the GSR signals are acquired while happy and grief of the subjects are elicited by video clips. Then the functional relation between emotional intensity and GSR feature is established, by fitting the feature values and the emotional intensity values of each emotional activity. According to this functional relation, the emotional intensity can be calculated in real time. Finally, we verify this method using new video clips. The results indicate that, the evaluation result of the model can reflect emotional intensity objectively, suggesting the feasibility of using physiological signals in real-life affective computing applications.