TY - JOUR T1 - Learning and visualizing user preferences over sets JF - American Association for Artificial Intelligence (AAAI) Y1 - 2007 A1 - Wagstaff,K. A1 - desJardins, Marie A1 - Eaton,E. A1 - Montminy,J. AB - In previous work, we introduced a representation language,DD-PREF, that balances preferences for particular items with preferences about the properties of the set. Specifically, DD- PREF permits the expression of preferences for depth (i.e., preferences for specific attribute values over others) and di- versity of sets (i.e., preferences for broad vs. narrow distri- butions of attribute values). We have also shown how pref- erences represented in DD-PREF can be learned from training data. In this paper, we present a new experimental method- ology, and give results in a Mars rover image domain. We also provide new visualizations of the learned preferences in this domain. Finally, we describe a Chinese restaurant menu domain for which we are currently gathering user data. ER -