Knowledgeable Explanations for Recommender Systems

Recommender Systems (RS) serve online customers in identifying those items from a variety of choices that best match their needs and preferences. In this context explanations summarize the reasons why a specific item is proposed and strongly increase the users´ trust in the system´s results. In this paper we propose a framework for generating knowledgeable explanations that exploits domain knowledge to transparently argue why a recommended item matches the user´s preferences. Furthermore, results of an online experiment on a real-world platform show that users´ perception of the usability of a recommender system is positively influenced by knowledgeable explanations and that consequently users´ experience in interacting with the system, their intention to use it repeatedly as well as their commitment to recommend it to others are increased.