The Emotional Computer Adaptive to Human Emotion

Abstract

Emotion provides an important context enabling people to understand each other, often hidden underneath their mind. Likewise, the computer needs to be more sympathetic to users’ commands in the context of their emotion. A challenging attempt has been made to develop an emotional computer, which reads physiological signals and analyzes them with respect to human emotion. Sensors were attached to an emotional mouse to measure photoplethysmogram, electrodermal activity and skin temperature. These physiological signals were read into on-line chip processors and evaluated by a rule base into human emotions. A two-dimensional emotion model was adopted and several empirical studies were performed to find out valid physiological patterns and to map them onto nine categories of human emotions. This study showed the feasibility of constructing the emotional computer adaptive to user emotion. Further research is needed before the emotional computer may come to the market.