A Computational Model of Narrative Generation for Surprise Arousal

This paper describes our effort for a planning-based computational model of narrative generation that is designed to elicit surprise in the reader´s mind, making use of two temporal narrative devices: flashback and foreshadowing. In our computational model, flashback provides a backstory to explain what causes a surprising outcome, while foreshadowing gives hints about the surprise before it occurs. Here, we present Prevoyant, a planning-based computational model of surprise arousal in narrative generation, and analyze the effectiveness of Prevoyant. The work here also presents a methodology to evaluate surprise in narrative generation using a planning-based approach based on the cognitive model of surprise causes. The results of the experiments that we conducted show strong support that Prevoyant effectively generates a discourse structure for surprise arousal in narrative.