No abstract

This paper describes work on automatically identifying categories of narrative clauses in personal stories written by ordinary people about their daily lives and experiences.

Interactive storytelling encompasses a wide variety of applications and systems that aim to allow players in a virtual world to affect the narrative progression prescribed by the author. The story world is often modeled by a set of hand-crafted causal and temporal relationships that define the possible narrative sequences based on the user's actions. In our view, a more promising approach involves applying methods from statistical language processing to create data-driven stories. Here, we explore integrating a typology of narrative clauses from Labov & Waletzky's theory of oral narrative(henceforth L&W) into the Say Anything data-driven storytelling approach. We show that we can automatically distinguish evaluation clauses from orientation and action clauses with 89% accuracy in fables, suggesting that it will be possible to develop new types of data-driven stories using L&W's typology.