Explainable recommendation attempts to develop models that generate not only high-quality recommendations but also intuitive explanations. It tries to address the problem of why: by providing explanations to users or system designers, it helps humans to understand why certain items are recommended by the algorithm, where the human can either be users or system designers. Explainable recommendation helps to improve the transparency, persuasiveness, effectiveness, trustworthiness, and satisfaction of recommendation systems, and facilitates system designers for better system debugging.
In recent years, a large number of explainable recommendation approaches have been proposed and applied in real-world systems. This survey provides a comprehensive review of the explainable recommendation research. The authors first highlight the position of explainable recommendation in recommender system research by categorizing recommendation problems into the 5W (what, when, who, where, and why). They then conduct a comprehensive survey of explainable recommendation on three perspectives: (1) a chronological research timeline of explainable recommendation; (2) a two-dimensional taxonomy to classify existing explainable recommendation research; (3) a summary of how explainable recommendation applies to different recommendation tasks. The authors also devote a section to discuss the explanation perspectives in broader IR and AI/ML research and end the survey by discussing potential future directions to promote the explainable recommendation research area and beyond.