Journal of Artificial Intelligence Research 21 (2004) 393-428 Submitted 07/03; published 03/04 A Personalized System for Conversational Recommendations Cynthia A. Thompson
[email protected] School of Computing University of Utah 50 Central Campus Drive, Rm. 3190 Salt Lake City, UT 84112 USA Mehmet H. G¨oker
[email protected] Kaidara Software Inc. 330 Distel Circle, Suite 150 Los Altos, CA 94022 USA Pat Langley
[email protected] Institute for the Study of Learning and Expertise 2164 Staunton Court Palo Alto, CA 94306 USA Abstract Searching for and making decisions about information is becoming increasingly dif- ficult as the amount of information and number of choices increases. Recommendation systems help users find items of interest of a particular type, such as movies or restau- rants, but are still somewhat awkward to use. Our solution is to take advantage of the complementary strengths of personalized recommendation systems and dialogue systems, creating personalized aides. We present a system – the Adaptive Place Advisor –that treats item selection as an interactive, conversational process, with the program inquir- ing about item attributes and the user responding. Individual, long-term user preferences are unobtrusively obtained in the course of normal recommendation dialogues and used to direct future conversations with the same user. We present a novel user model that influ- ences both item search and the questions asked during a conversation. We demonstrate the effectiveness of our system in significantly reducing the time and number of interactions required to find a satisfactory item, as compared to a control group of users interacting with a non-adaptive version of the system.