There´s always hope: Enhancing agent believability through expectation-based emotions

To endow virtual agents with more realistic affective behavior, the notion of expectation-based emotions plays an important role: emotional states of agents should not only be triggered by present stimuli, but also by anticipation on future stimuli, and evaluation of past stimuli in the context of these anticipations. Within this study, an extension of the belief-desire-intention (BDI) model with expectation-based emotions is proposed. The model has been implemented in the modeling language LEADSTO. In addition, a game application has been developed, in which a user can play a dice game against an agent that is equipped with the emotion-based model. An empirical evaluation indicates that the model significantly enhances the agent´s believability, in particular concerning its involvement in the situation.