Multigenre AI-powered Story Composition
This addresses the challenge of maintaining genre coherence in AI-generated interactive stories, though it appears incremental as it builds on existing genre classifications and methods.
The paper tackles the problem of ensuring thematic consistency in interactive story composition by constructing genre patterns, using a two-phase process with AI agents to generate stories from user premises while accommodating suggestions.
This paper shows how to construct genre patterns, whose purpose is to guide interactive story composition in a way that enforces thematic consistency. To start the discussion we argue, based on previous seminal works, for the existence of five fundamental genres, namely comedy, romance - in the sense of epic plots, flourishing since the twelfth century -, tragedy, satire, and mystery. To construct the patterns, a simple two-phase process is employed: first retrieving examples that match our genre characterizations, and then applying a form of most specific generalization to the groups of examples in order to find their commonalities. In both phases, AI agents are instrumental, with our PatternTeller prototype being called to operate the story composition process, offering the opportunity to generate stories from a given premise of the user, to be developed under the guidance of the chosen pattern and trying to accommodate the user's suggestions along the composition stages.