A taxonomy for generating explanations in recommender systems

Abstract

In recommender systems, explanations serve as an additional type of information that can help users to better understand the system's output and promote objectives such as trust, confidence in decision making, or utility. This article proposes a taxonomy to categorize and review the research in the area of explanations. It provides a unifed view on the different recommendation paradigms, allowing similarities and differences to be clearly identified. Finally, the authors present their view on open research issues and opportunities for future work on this topic. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.