User interest modeling for social TV-recommender systems based on audiovisual consumption

This paper presents an innovative consumption-modeling system applied to digital TV, able to infer the user interest regarding the TV contents. The user interest inferred is used to feed content recommender systems, and it has been tested in real scenarios involving real users. The modeling system uses as input the TV consumption data and performs an algorithm based on a Hidden Markov Model and Bayesian inference techniques to infer the said user interest. Real data have been picked up in real time to feed our modeling, and the final results have been checked comparing with user’s tastes, which have been expressed through a set of questionnaires and the whole system has been tested in a TV broadcasting scenario with real users. Conclusions show that our system improves the reliability from classic user interest modeling systems (they are mainly based on explicit opinion based methods, which can be intrusive for general users and could show certain deceptive results, as it is described in this paper).