Application of Support Vector Machine for Emotion Classification

Emotions are a great source of information in communication and interaction among people. There is a continuous interaction between emotions, thoughts and behavior, in such a way that they constantly influence each other. In this paper, we propose an emotion classification system that can classify four emotions (happiness, sadness, fear and anger). Participants' physiological signals are acquired by electrocardiogram (ECG), galvanic skin responses (GSR), blood volume pulse (BVP), and pulse. We adopt sequential floating forward selection (SFFS) and F-score feature selection methods to get discriminative features that influence emotion. The selected features are used to train the support vector machine (SVM) classifier. Experiment results show that the proposed method achieves 89.6%.