A Formalization of Emotional Planning for Strong-Story Systems

Abstract

Characters that are capable of expressing emotions seem more lifelike to a human audience. Interacting with emotional characters may cause a human user to feel empathy and to care for their fate. In turn, the audience may feel more engaged in the story. We take a step to address the lack of computational models of emotions for strong-story systems and propose to extend strong-story state-space narrative planners, already equipped with intentionality and belief, to reason about character emotions. Our proposed system is multi-agent, highly domain-independent, and focused on reasoning and decision making. In this paper, we evaluate to what extent our system can accurately model a set of emotions and in doing so, improve the believability of story characters.

Sabre: A Narrative Planner Supporting Intention and Deep Theory of Mind

“…We validated this model of believable actions with human subjects (Shirvani, Farrell, and Ware 2018), but we also acknowledge believable character behavior is more than simply seeking higher utilities. Parallel work is using Sabre to expand our definition to include emotion and personality (Shirvani and Ware 2020).…”