User modelling is both a key component and important challenge in designing personalised
virtual assistants. Thankfully, talking to a user (using a conversational interface such as a
dialogue model) can allow an agent to better understand their beliefs, needs, and desires.
Zuckerman and Litman (2001) [1] provide some insight into how to use natural language to
create and maintain a user model.
The aim of this project is to improve this model of the user, by being able to expand upon the
type of information the model has access to, either by using affect (emotions/feelings),
creating more informative heuristics, or introducing post-processing.
References:
[1] Zukerman, Ingrid, and Diane Litman. “Natural language processing and user modeling: Synergies and limitations.” User modeling and user-adapted interaction 11.1 (2001): 129-158.