Using Gross' Emotion Regulation Theory to Advance Affective Computing

Abstract

Affective computing is the study and development of systems that are able to interpret, recognize, process, and simulate human affects. Several researchers have pointed out that affective computing, and computational modeling of emotions in particular, is highly fragmented and that models that are built are rarely incremental or contrasted with one another. Moreover, even though emotion regulation is seen as an important aspect of emotion, almost no models of emotion regulation exist. This thesis tries to advance the field of computational modeling of emotion using the theory of emotion regulation by Gross. First, the theory by Gross is fit into the landscape of emotion theory. In particular, Gross’ theory is compared with the theory by Lazarus, Frijda and the OCC and the difference between coping and emotion regulation is investigated. Then, some models of emotion are compared with one another based upon the results found. Finally it is shown how the ideas of Gross can be used to modify and extend already two existing models: EMA and the formalization of Broekens et al. This thesis does not only focus on the results obtained, but also on developing constructive methods to compare and extend theories and models, which is believed to also contributed to advancing affective computing.