Explainable Entity-based Recommendations with Knowledge Graphs
This addresses the challenge of explainable recommendations in scenarios lacking user reviews, which is important for improving transparency and trust in recommendation systems.
The paper tackles the problem of generating explanations for recommendations when review text is unavailable by leveraging external knowledge graphs, resulting in a method that jointly ranks items and entities using Personalized PageRank to produce recommendations with explanations.
Explainable recommendation is an important task. Many methods have been proposed which generate explanations from the content and reviews written for items. When review text is unavailable, generating explanations is still a hard problem. In this paper, we illustrate how explanations can be generated in such a scenario by leveraging external knowledge in the form of knowledge graphs. Our method jointly ranks items and knowledge graph entities using a Personalized PageRank procedure to produce recommendations together with their explanations.