User - interface agent interaction: personalization issues

Interface agents are computer programs that provide personalized assistance to users with their computer-based tasks. Most interface agents achieve personalization by learning a user’s preferences in a given application domain and assisting him according to them. In this work we adopt a different approach to personalization: how to personalize the interaction between interface agents and users in a mixed-initiative interaction context. We have empirically studied a set of interaction issues that agents have to take into account to achieve this goal and we present our results in this article. Some of these personalization issues are: discovering the type of assistant a user wants, learning when (and if) to interrupt the user, discovering how the user wants to be assisted in different contexts. As a result of our experiments, we have defined the components of a user interaction profile that models a user’s interaction and assistance preferences. This profile will enable interface agents to enhance and personalize their interaction with users by discovering how to provide each user assistance of the right sort at the right time. r 2003 Elsevier Ltd. All rights reserved.