Abstract
In this work we explore the use of a Constraint Programming (CP) model for the selection of suitable filmic content to use to output a horror narrative in a way that is personalised to a particular viewer type. We adopt a bipartite representation of narrative where planning is used to generate an outline narrative and then CP is used to build the discourse presentation: the filmic variant that is presented to the viewer. In the paper we overview our model and illustrate it with example horror variants generated by our prototype system. We also present an analysis of sample filmic sequences output by the system along with the results of a small user evaluation which demonstrate the potential of the approach.
Computer Scientist
My research interests include software reliability, software verification, and formal methods applied to software engineering. I am also interested in interactive storytelling. For more details, see some of my projects or my selected (or recent) publications. More posts are available in my blog. Follow me on Twitter or add me on LinkedIn.