Semi-automatic task recognition for interactive narratives with EAT & RUN
Jeff Orkin, Tynan Smith, Hilke Reckman, Deb Kumar Roy · 2010
Mining data from online games provides a potential alternative to programming behavior and dialogue for characters in interactive narratives by hand. Human annotation of course-grained tasks can provide explanations that make the data more useful to an AI system, however human labor is expensive. We describe a semi-automatic methodology for recognizing tasks in gameplay traces, including an annotation tool for non-experts, and a runtime algorithm. Our results show that this methodology works well with a large corpus from one game, and suggests the possibility of refactoring the development process for interactive narratives.