A computational model for finding the tilt in an improvised scene

Improvisational theatre (improv) is a real world example of an interactive narrative environment that has a strong focus on the collaborative construction of narrative as a joint activity. Although improv has been used as an inspiration for computational approaches to interactive narrative in the past, those approaches have generally relied on shallow understandings of how theatrical improvisation works in terms of the processes and knowledge involved. This paper presents a computational model for finding the tilt in a narrative environment with no pre-authored story structures, based on our own cognitively-based empirical studies of real world improvisers.