Towards generating narratives for the real world

Abstract

An immersive, interactive environment and the non-player characters populating it often play a key role in interactive narrative experiences. We posit that if a procedurally generated narrative is better able to reflect real-world attributes of the players surroundings, then the experience would be more transportive for the player. With this comes the problem of generating believable narratives and characters for an open, complex, real world. Simulating such a society within the constraints of the real environment, and allowing for virtual characters to more accurately mimic human behavior could increase the believability of the agents. The interactions amongst these agents sharing their cultural views, biases, and histories based on their real-world geolocation could inform the study of audience modeling and machine enculturation, allowing computers to learn or reason about social norms in regions. Finally, we posit this research would afford better applications in the field of entertainment or computational social science.