An Algorithm Independent Case-Based Explanation Approach for Recommender Systems Using Interaction Graphs

Explanations in recommender systems are essential to improve user confidence in the recommendation. Traditionally, recommendation algorithms are based on ratings or additional information about the item features or the user profile. But some of these approaches are implemented as black boxes where this information is not available to provide the explanations. In this work, we propose a case-based approach to support this kind of black-box recommenders in order to find explanatory examples. It is a knowledge-light approach that only requires the information extracted from the interactions between users and items. As these interaction graphs can be analyzed through social network analysis, we propose the use of link prediction techniques to find the most suitable explanatory cases for a recommended item.