A Goal-Based Model of Personality for Planning-Based Narrative Generation

We present an approach to incorporate interesting and compelling characters in planning-based narrative generation. The approach is based on a computational model that utilizes character actions to portray these as having distinct and well-defined personalities. Well-developed characters have features that enable them to significantly enhance the believability and quality of a story. In this paper we present a computational model aimed at facilitating the inclusion of compelling characters in narratives that are automatically generated by a planning-based system. In this model, personality is operationalized as behavior that results from choices made by a character in the course of a story. This operationalization uses the taxonomy defined in the Five-Factor Model (FFM) (Goldberg 1990) and results from behavioral psychology that link behavior to personality traits (Mehl, Gosling, and Pennebaker 2006). The model focuses on the role that actions performed by characters play over the course of a narrative in the construction of the mental model of the story that the audience forms when experiencing it. In this model, the mechanism that generates the story is designed to ensure that the story structure and its contents promote the existence of choices for character’s actions and make such existence evident to the audience by including contrasting options available to the character. The actions that characters perform are chosen by an intelligent mechanism that ensures their consistency with the personality traits assigned to the character by a human author prior to story generation.