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.
|Publication status||Published - 2017|
|Event||Workshop on Constraint Satisfaction Techniques for Planning and Scheduling Problems 2017 - Pittsburgh, United States|
Duration: 19 Jun 2017 → 20 Jun 2017
|Workshop||Workshop on Constraint Satisfaction Techniques for Planning and Scheduling Problems 2017|
|Abbreviated title||COPLAS 2017|
|Period||19/06/17 → 20/06/17|