TV program recommender using user authentication on middleware Ginga

The system proposed in this article aims to identify and recognize television users with the objective of offering personalized television programming. In this setting, the authentication and recommendation mechanisms used require to collect the necessary information in an implicit manner as much as possible, such that the leisure and entertainment objectives this broadcasting medium brings are not interrupted. The design proposed for the implementation of the interactive application uses an authentication process based on facial recognition and a recommendation algorithm based on contextual information, which is mainly implicitly captured. Experimental obtained results show that the system offers more accurate recommendations when the user exhibits a habitual behavior; e.g. watching TV programs of a same category in a specific channel and schedule.