Searching for Storiness: Story-Generation from a Reader’s Perspective

Abstract

Previous work in the field of automatic story-generation has largely neglected reader-response as an important aspect of the success of a story. This paper describes an approach to automatic story-generation based on an intuitive model of the cognitive states and processes within the mind of an imagined reader of the story. Generation assumes a privileged access to the responses of the reader, and proceeds by heuristically searching for story elements which create preferred abstract ‘storiness’ effects for the reader. It is claimed that the model is sensitive to the idiosyncracies of individual readers, but also that it captures useful general properties of stories. Previous work in the field of automatic story-generation is briefly reviewed, and this new model is placed in context. The model is then motivated, and described in more detail. Finally, the strengths and weaknesses of the model are discussed, and issues of implementation are summarised. The model described in this paper is work-in-progress as part of a PhD at the University of Edinburgh.