We present a probabilistic model, based on Dynamic Decision Networks, to assess user affect from possible causes of emotional arousal. The model relies on the OCC cognitive theory of emotions and is designed to assess student affect during the interaction with an educational game. A key element of applying the OCC theory to assess user affect is knowledge of user goals. Thus, in this paper we focus on describing how our model infers these goals from user personality traits and interaction behavior. In particular, we illustrate how we iteratively defined the structure and parameters for this part of the model by using both empirical data collected through Wizard of Oz experiments and relevant psychological findings.

We describe preliminary research on devising intelligent agents that can improve the educational effectiveness of collaborative, educational computer games. We illustrate how these agents can overcome some of the shortcomings of educational games by explicitly monitoring how students interact with the games, by modeling both the students' cognitive and emotional states, and by generating calibrated interventions to trigger constructive reasoning and reflection when needed. Introduction In this paper, we explore the potential of enriching educational computer games with socially intelligent agents that can help students learn effectively from the games while maintaining the high level of engagement and motivation that constitutes the strong appeal of electronic games in non-educational settings. Our research is developed in the context of EGEMS, the Electronic Games for Education in Math and Science project at the University of British Columbia (UBC). EGEMS is an interdisciplinary pro...