Evaluating critiquing-based recommencler agents

We describe a user study evaluating two critiquing-based recommender agents based on three criteria: decision accuracy, decision effort, and user confidence. Results show that user-motivated critiques were more frequently applied and the example critiquing system employing only this type of critiques achieved the best results. In particular, the example critiquing agent significantly improves users' decision accuracy with less cognitive effort consumed than the dynamic critiquing recommender with system-proposed critiques. Additionally, the former is more likely to inspire users' confidence of their choice and promote their intention to purchase and return to the agent for future use. Copyright © 2006, American Association for Artificial Intelligence (www.aaai.org). All rights reserved.