Evolving Story Narrative using Surrogate Models of Human Judgement

Communication has been an active field of research in Robotics. However, less work has been done in the ability of robots to negotiate meanings of the world through storytelling. In this paper, we address this gap from the perspective of evolving stories. By approximating human evaluation of stories to guide the evolution, we can automate the story evolutionary process without interacting with humans. First, a multi-objective story evolution approach is applied where the approximated human story evaluation model automatically evaluates the subjective story metrics such as coherence, novelty and interestingness. We then use humans again to validate the stories narrated by the machine. Results show that for each of the human subjects, the stories collected after story evolution are regarded as better stories compared to the initial stories. Some interesting relationships are revealed and discussed in details.