A Data-Driven Case-Based Reasoning Approach to Interactive Storytelling

Abstract

Abstract. In this paper we describe a data-driven interactive storytelling system similar to previous work by Gordon & Swanson. We addresses some of the problems of their system, by combining information retrieval, machine learning and natural language processing. To evaluate our system, we leverage emerging crowd-sourcing communities to collect orders of magnitude more data and show statistical improvement over their system. The end result is a computer agent capable of contributing to stories that are nearly indistinguishable form entirely human written ones to outside observers.

Planning Technologies for Interactive Storytelling

“…Despite the wide-scale adoption of planning, other techniques have been proposed for narrative in IS such as Branching Narrative Structures [Hill et al (2001); Spierling et al (2006)], Behaviour Trees [Champandard (2008);LLansó et al (2009)], Bayesian Networks [Arinbjarnar and Kudenko (2010); Sparacino (2003)], Case-based Reasoning [Gervás et al (2005); Swanson and Gordon (2010)], Assumption Based Truth Maintenance Systems [Sgouros et al (1996)] and Monte-Carlo Tree Search [Kartal et al (2014)].…”