Evaluation, Orientation, and Action in Interactive StoryTelling
DOI:
https://doi.org/10.1609/aiide.v9i4.12632Keywords:
Data-Driven StoryTelling, Natural Language Processing, Machine LearningAbstract
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.