Interactive Critiquing forCatalog Navigation in E-Commerce
Artificial Intelligence Review
VISCORS: A Visual-Content Recommender for the Mobile Web
IEEE Intelligent Systems
Acquiring and Revising Preferences in a Critique-Based Mobile Recommender System
IEEE Intelligent Systems
International Journal of Electronic Commerce
Replaying live-user interactions in the off-line evaluation of critique-based mobile recommendations
Proceedings of the 2007 ACM conference on Recommender systems
Preference-Based Organization Interfaces: Aiding User Critiques in Recommender Systems
UM '07 Proceedings of the 11th international conference on User Modeling
The adaptive web
Conversational Case-Based Recommendations Exploiting a Structured Case Model
ECCBR '08 Proceedings of the 9th European conference on Advances in Case-Based Reasoning
Rush: repeated recommendations on mobile devices
Proceedings of the 15th international conference on Intelligent user interfaces
A diary study of understanding contextual information needs during leisure traveling
Proceedings of the third symposium on Information interaction in context
Design and evaluation of a command recommendation system for software applications
ACM Transactions on Computer-Human Interaction (TOCHI)
Hi-index | 0.00 |
User preferences acquisition plays a very important role for recommender systems. In a previous paper, we proposed a critique-based mobile recommendation methodology exploiting both long-term and session-specific user preferences. In this paper, we evaluate the impact on the recommendation accuracy of the two kinds of user preferences. We have ran off-line experiments exploiting the log data recorded in a previous live-user evaluation, and we show here that exploiting both long-term and session-specific preferences results in a better recommendation accuracy than using a single user model component. Moreover, we show that when the simulated user behavior deviates from that dictated by the acquired user model the session-specific preferences are more useful than the long-term ones in predicting user decisions.