In this paper, we describe our contribution to the 2015 Linked Data Mining Challenge. The proposed task is concerned with the prediction of review of movies as \good" or \bad", as does Metacritic website based on critics' reviews. First we describe the sources used to build the training data. Although, several sources provide data about movies on the Web in different formats including RDF, data from HTML pages had to be gathered to fulfill some of our features. We then describe our experiment training a decision tree model on 241 features derived from our RDF knowledge base, achieving an accuracy of 0.94