Publication Details

Evaluating User-Adaptive Systems: Lessons from Experiences with a Personalized Meeting Scheduling Assistant

by Berry, P. and Donneau-Golencer, T. and Duong, K. and Gervasio, M. and Peintner, B. and Yorke-Smith, N.

in Proceedings of the Twenty-First International Conference on Innovative Applications of Artificial Intelligence (IAAI’09)

Abstract

We discuss experiences from evaluating the learning performance of a user-adaptive personal assistant agent. We discuss the challenge of designing adequate evaluation and the tension of collecting adequate data without a fully functional, deployed system. Reflections on negative and positive experiences point to the challenges of evaluating user-adaptive AI systems. Lessons learned concern early consideration of evaluation and deployment, characteristics of AI technology and domains that make controlled evaluations appropriate or not, holistic experimental design, implications of "in the wild" evaluation, and the effect of AI-enabled functionality and its impact upon existing tools and work practices.

Electronic Copies

Adobe PDF

BibTeX

EndNote

Associated Projects

Cognitive Assistant that Learns and Organizes As part of DARPA’s Personalized Assistant that Learns (PAL) program, SRI and team members are working on developing a next-generation "Cognitive Agent that Learns and Organizes" (CALO).

AIC Personnel

	Name	Title	E-mail
	Berry, Pauline M	Alumnus
	Donneau-Golencer, Thierry David	Alumnus
	Duong, Khang	Software Engineer II
	Gervasio, Melinda	Senior Computer Scientist
	Peintner, Bart	Sr. Computer Scientist
	Yorke-Smith, Neil	Computer Scientist