Narrative Variations in a Virtual Storyteller
This work addresses the challenge of automated storytelling for applications in entertainment or education, but it is incremental as it builds on existing narratological distinctions.
The researchers tackled the problem of generating varied narrative tellings in a virtual storyteller by creating Fabula Tales, a computational framework that implements narratological variations like direct vs. indirect speech and point of view, and showed that different tellings affect readers' perceptions of stories and characters.
Research on storytelling over the last 100 years has distinguished at least two levels of narrative representation (1) story, or fabula; and (2) discourse, or sujhet. We use this distinction to create Fabula Tales, a computational framework for a virtual storyteller that can tell the same story in different ways through the implementation of general narratological variations, such as varying direct vs. indirect speech, character voice (style), point of view, and focalization. A strength of our computational framework is that it is based on very general methods for re-using existing story content, either from fables or from personal narratives collected from blogs. We first explain how a simple annotation tool allows naive annotators to easily create a deep representation of fabula called a story intention graph, and show how we use this representation to generate story tellings automatically. Then we present results of two studies testing our narratological parameters, and showing that different tellings affect the reader's perception of the story and characters.