User profiling for TV program recommendation based on hybrid television standards using controlled clustering with genetic algorithms and artificial neural networks

Abstract

In this paper, an earlier method proposed by the authors to make smart recommendations utilizing artificialintelligence and the latest technologies developed for the television area is expanded further using controlled clusteringwith genetic algorithms (CCGA). For this purpose, genetic algorithms (GAs), artificial neural networks (ANNs), andhybrid broadcast broadband television (HbbTV) are combined to get the users’ television viewing habits and to createprofiles. Then television programs are recommended to the users based on that profiling. The data gathered by thedeveloped HbbTV application for previous studies are reused in this study. These data are employed to cluster users.The number of clusters is found by CCGA, a method proposed in this paper. For each cluster formed by CCGA, aseparate ANN is designed to learn the viewing habits of the users of the corresponding cluster. The weight matricesare initialized also by GA. The recommendations produced using the proposed model are then presented by the sameHbbTV application developed by the authors. Clustering with GAs gives better results when compared to the well-knownK-means clustering algorithm.