Validation of a Model for Coping and Mood for Virtual Agents

In order to make believable virtual agents, the incorporation of emotions within these agents is often said to be of crucial importance. A variety of computational models have been proposed for emotions, however the validation of these models is mostly limited to the validation of the overall behavior of the agent incorporating these emotions (e.g. evaluating whether the overall behavior is realistic or human like). Ideally, the validation would also investigate whether the strength of the generated emotions matches the emotions displayed by humans. Hereby, two approaches can be followed: (1) looking at average behavior of humans and seeing whether the emotions models exhibit similar patterns, and (2) trying to see whether the emotion models can replicate the emotions of individual humans with their own personality and characteristics. In this paper, the latter approach is taken. An experiment has been designed in the context of depression whereby humans were regularly asked to rate their emotions when undergoing therapy. Parameter estimation techniques have been used to tune an existing model for emotions towards the observed patterns. The results show that the model can describe the human´s emotions accurately and is even able to make predictions of future emotional states in quite a precise manner.