Stories from Games: Content and Focalization Selection in Narrative Composition

Game logs could be exploited as a source for reflection on user performance, with a view to improvement or simply the additional entertainment of reminescing. Yet in their raw form they are difficult to interpret, and sometimes only specific parts of the game are worth reviewing. The ability to produce textual narratives that rework these logs (or the interesting parts of them) as stories could open up this wealth of data for further use. This paper presents a model of the task of narrative composition as a set of operations that need to be carried out to obtain a linear sequence of event descriptions from a set of events that inspire the narration. As an indicative case study, an initial implementation of the model is applied to a chess game understood as a formalised set of events susceptible of story-like interpretations. Operating on simple representations of a chess game in algebraic notation, exploratory solutions for the tasks of content selection are explored based on a fitness function that aims to reflect some of the qualities that humans may value on a discourse representation of a story.