Personalized Web recommendations: supporting epistemic information about end-users

The online recommendations are a popular presence in the Web sites world due to their potential to increase the customers' satisfaction. The ability to represent epistemic information about the clients' beliefs is important to understand their needs. This paper presents a recommender system based on reinforcement learning. The system represents concepts presented on a Web site by epistemic logical programs and uses a similarity measure between programs in order to facilitate generalization. A prototype of this system and experiments are presented.