A New Approach to Emotion Assessment Based on Biometric Data

Abstract

Several knowledge areas such as psychology, medicine and computer science have been devoting serious efforts regarding emotional state definition, identification and assessment. This project consists in an automatic emotion assessment tool based on biometric data acquisition supported by low-budget biometric devices as a electroencephalograph and a galvanic skin response. The classification is grounded on data analysis and processing of standard emotional induction methods. The numerous conducted experimental sessions,alongside with the developed support tools, allowed the extraction of conclusions such as the capability of effectively performing automatic classification of the subjectpsilas predominant emotional state. The developed tool's success rate, validated against self assessment interviews, was approximately 75%. It was also experimentally concluded that female subjects are emotionally more active and easily induced than males.