The presence of interesting and compelling characters is an essential component of effective narrative. Well-developed characters have features that enable them to significantly enhance the believability and quality of a story. In this paper, we describe the results of an experiment to evaluate a planning-based narrative generation system that focuses on the generation of stories that express character. The system is designed to automatically produce narratives that show character personality traits through the choices characters make when selecting the means by which they achieve their goals. Results from our study support the hypothesis that an audience presented with stories generated by Mask will attribute personality traits to the story characters that have significant correlation with the computational model of personality used to drive the characters' choices.
My thesis aims at conceptualizing and implementing a computational model of narrative generation that is informed by narratological theory as well as cognitive multi-agent simulation models. It approaches this problem by taking a mimetic stance towards fictional characters and investigates how narrative phenomena related to characters can be computationally recreated from a deep character model grounded in multi agent systems. Based on such a conceptualization of narrative it explores how the generation of plot can be controlled, and how the quality of the resulting plot can be evaluated, in dependence of fictional characters. By that it contributes to research on computational creativity by implementing an evaluative storytelling system, and to narratology by proposing a generative narrative theory based on several post-structuralist descriptive theories.
Walker, Marilyn (University of California, Santa Cruz) | Lin, Grace (University of California, Santa Cruz) | Sawyer, Jennifer (University of California, Santa Cruz) | Grant, Ricky (University of California, Santa Cruz) | Buell, Michael (University of California, Santa Cruz) | Wardrip-Fruin, Noah (University of California, Santa Cruz)
Interactive Narrative often involves dialogue with virtual dramatic characters. In this paper we compare two kinds of models of character style: one based on models derived from the Big Five theory personality, and the other derived from a corpus-based method applied to characters and films from the IMSDb archive. We apply these models to character utterances for a pilot narrative-based outdoor augmented reality game called Murder in the Arboretum . We use an objective quantitative metric to estimate the quality of a character model, with the aim of predicting model quality without perceptual experiments. We show that corpus-based character models derived from individual characters are often more detailed and specific than personality based models, but that there is a strong correlation between personality judgments of original character dialogue and personality judgments of utterances generated for Murder in the Arboretum that use the derived character models.
Character intention revision is an essential component of stories, but it has yet to be incorporated into story generation systems. However, intentionality, one component of intention revision, has been explored in both narrative generation and logical formalisms. The IRIS system adopts the belief/desire/intention framework of intentionality from logical formalisms and combines it with preexisting concepts of intentionality in narrative. IRIS also introduces the crucial concept of intention revision for characters in the story. The intent of this synthesis is to create stories with dynamic and believable characters that update their beliefs, replan, and revise their intentions over the course of the story.