A recommender system based on implicit feedback for selective dissemination of ebooks

In this study, we describe a recommendation system for electronic books. The approach is based on implicit feedback derived from user's interaction with electronic content. User's behavior is tracked through several indicators that are subsequently used to feed the recommendation engine. This component then provides an explicit rating for the material interacted with. The role of this engine could be modeled as a regression task where content is rated according to the mentioned indicators. In this context, we benchmark twelve popular machine learning algorithms to perform this final function and evaluate the quality of the output provided by the system.