Using Topic Hierarchies with Privileged Information to Improve Context-Aware Recommender Systems

Recommender systems are designed to assist individuals to identify items of interest in a set of options. A context-aware recommender system makes recommendations by incorporating available contextual information into the recommendation process. One of the major challenges in context-aware recommender systems research is the lack of automatic methods to obtain contextual information for these systems. Considering this scenario, in this paper, we propose to use contextual information from topic hierarchies to improve the performance of context-aware recommender systems. Three different types of topic hierarchies are constructed by using the LUPI-based Incremental Hierarchical Clustering method: a topic hierarchy using only a traditional bag-of-words, a second topic hierarchy using a bag-of-words of named entities and a third topic hierarchy using both information. We evaluate the contextual information in four context-aware recommender systems. The empirical results demonstrate that by using topic hierarchies we can provide better recommendations.