Toward Affective Dialogue Modeling using Partially Observable Markov Decision Processes
Trung Bui, Job Zwiers, Mannes Poel, Anton Nijholt · University of Twente Research Information · 2006
Abstract. We propose a novel approach to developing a dialogue model which is able to take into account some aspects of the user’s emotional state and acts appropriately. The dialogue model uses a Partially Observable Markov Decision Process approach with observations composed of the observed user’s emotional state and action. A simple example of route navigation is explained to clarify our approach and preliminary results & future plans are briefly discussed. 1