Creativity has been proclaimed as a grand challenge for research in both artificial intelligence (in the form of computational creativity) and human-computer interaction (in the form of creativity support tools). Storytelling is an exemplary creative domain: stories are complex creative artifacts in which many different facets—including theme, plot, character, and narration—must all be brought into alignment for the story as a whole to succeed. Consequently, the development of intelligent narrative technologies represents an excellent way to improve our understanding of creativity as a computational problem. In this dissertation, I discuss my work on the use of AI to provide plot-level creativity support for creative writing—particularly through the implementation of story sifters, which can interactively or autonomously identify sites of narrative potential within large corpuses of potentially narratable events. By crafting human-playable narrative instruments (systems that can be played to produce narrative, much like musical instruments can be played to produce music) based on story sifting technologies, I illustrate how AI can help players refine vague high-level plot ideas into coherent narrative throughlines—resulting in a new form of playful AI-supported co-creative writing, with design implications for AI-based creativity support tools in a wide variety of creative domains.

Prior interactive narrative research has extensively investigated the question of how game designers can tell stories through games, but little investigation has been done of how and why players use games to tell stories of their own. This thesis investigates player storytelling practices around emergent narrative games as a form of authorship play. First, we examine existing play practices centered on the authorship of written stories based on play experiences. We find that some players deliberately seek out emergent narrative games as storytelling partners, and argue that this is due in part to the creativity support features common to several games within this genre, which can help players overcome certain barriers to creativity—including fear of the blank canvas, fear of judgment, writer's block, and perfectionism. Second, we present Why Are We Like This? (WAWLT), a mixed-initiative co-creative storytelling game based on design insights gleaned from this analysis. We discuss the AI architecture of WAWLT, focusing especially on how it makes use of story sifting and social simulation technologies to provide players with creativity support, and present the results of preliminary playtesting. Finally, we conclude with some brief discussion of the implications of our work in this design space, including our priorities for future work.