MovieCommenter: Aspect-based collaborative filtering by utilizing user comments

Collaborative filtering relies on numerical ratings for recommendations. While users consider various aspects of content as a basis of their evaluation, a numeric rating provides only an aggregated report of final assessment. The performance of a collaborative recommender system could be enhanced if the ratings are augmented by more specific information used for evaluation. In this paper, we present MovieCommenter, a recommender system that utilizes movie aspects - key features and users' opinions about the movie. We conducted a series of experiments to perform both qualitative and quantitative evauations of the system performance. The results show that our approach makes more precise recommendations than traditional approaches. Moreover, the interface of MovieCommenter was found to enhance the recommendation explanability, ability to explain how the recommendation was made. Because our approach is based on independent schema, this approach could be easily applied for recommending other domain contents.