Sto(ry)chastics: A Bayesian Network Architecture for User Modeling and Computational Storytelling for Interactive Spaces

This paper presents sto(ry)chastics, a user-centered approach for computational storytelling for real-time sensor-driven multimedia audiovisual stories, such as those that are triggered by the body in motion in a sensor-instrumented interactive narrative space. With sto(ry)chastics the coarse and noisy sensor inputs are coupled to digital media outputs via a user model, which is estimated probabilistically by a Bayesian network. To illustrate sto(ry)chastics, this paper describes the museum wearable, a device which delivers an audiovisual narration interactively in time and space to the visitor as a function of the estimated visitor type. The wearable relies on a custom-designed long-range infrared location-identification sensor to gather information on where and how long the visitor stops in the museum galleries and uses this information as input to, or observations of, a (dynamic) Bayesian network. The network has been tested and validated on observed visitor tracking data by parameter learning using the Expectation Maximization (EM) algorithm, and by performance analysis of the model with the learned parameters.