Evaluating the Combination of Multiple Metadata Types in Movies Recommendation

This paper proposes a study and comparison of the combination of multiple metadata types to improve the recommendation of movie items according to users' preferences. We used four algorithms available in the literature to analyze the descriptions, and compared each other using all the possible combinations of the metadata extracted from two datasets, namely MovieLens and IMDB. As a result of our evaluation, we found out that combining metadata generates better predictions for the considered content-based recommenders.