EEG-based Emotion Word Recognition

Emotion recognition rapidly gains interest from research community, which gives computer the ability to recognize, understand, express, and adapt to human emotions to help computer more intelligent. Traditional emotion recognition modalities (e.g. face and voice) always could not identify the totally true emotion state. Recently, with the development of electroencephalogram (EEG) equipment, utilizing EEG signals to build emotion recognition system is more and more feasible and meaningful. In this paper, an abstract emotional words classification task is designed, which requires participants judge the emotion polarity (positive or negative) for given words. Based on EEG signals, a series of study is re-explored, including data collecting, feature extraction, feature selection, and classification model. Furthermore, the Event Related Potential (ERP) components and behavioral data analysis uncover some meaningful conclusion on emotion recognition.