Sistema de recomendación de contenidos audiovisuales: Algoritmo de inferencia semántica

Abstract

This article presents the analysis of a Semantic Inference Algorithm used in an Audiovisual Content Recommender System in the domain of Digital Television. The obtained results show that the inclusion of distinct semantic properties and their combinations lead to a considerable reduction of the Mean Absolute Error (MAE) obtained for user rating prediction computation and that the semantic property Actor has the major influence over recommendation estimation.