Taxonomy Based Personalized News Recommendation: Novelty and Diversity

Recommender systems are designed to help users quickly access large volumes of information according to their profiles. Most previous works in recommender systems have put their emphasis on the accuracy of finding the most similar items according to a user's profile, while often ignoring other aspects that may affect users' experiences in practice, e.g., the novelty and diversity issues within a recommendation list. In this paper, we focus on utilizing taxonomic knowledge extracted from an online encyclopedia to boost a content-based personalized news recommender system without much human involvement. Given a recommendation list, we improve a user's satisfaction by introducing the taxonomy based novelty and diversity metrics to include novel, but potentially related items into the list, and filter out redundant ones. The experimental results show that the coarse grained knowledge resources can help a content-based news recommender system provides accurate as well as user-oriented recommendations.