Preference Learning for Adaptive Interaction

Julie S. Weber

This extended abstract describes ongoing work in the development of an intelligent assistant that interacts with its user in a personalized fashion, deciding whether, when and how to interact based on a user's needs and preferences. I consider two types of users: people who work in an office environment and require assistance with managing their daily meeting and project schedule, and people with cognitive disabilities who require guidance in performing their daily tasks. I will examine various interaction types including reminders, requests for confirmation of a task having been completed, requests for permission to assist in the performance of a task, and requests for feedback. Both explicitly stated and implicit user preferences will be used as input to the learning mechanism, and the assistant will be evaluated based on its learning efficiency and the level of user satisfaction it achieves. This development of a preference learning model for interaction management constitutes the primary contribution of my work.

Subjects: 7.2 Software Agents; 3. Automated Reasoning

Submitted: May 15, 2007

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.