Explainable Recommendation: A Survey and New Perspectives (Foundations and Trends(r) in Information Retrieval)

Explainable Recommendation refers to the personalized recommendation algorithms that address the problem of why -- they not only provide the user with the recommendations, but also make the user aware why such items are recommended by generating recommendation explanations, which help to improve the effectiveness, efficiency, persuasiveness, and user satisfaction of recommender systems. In recent years, a large number of explainable recommendation approaches -- especially model-based explainable recommendation algorithms -- have been proposed and adopted in real-world systems. In this survey, we review the work on explainable recommendation that has been published in or before the year of 2018. We first high-light the position of explainable recommendation in recommender system research by categorizing recommendation problems into the 5W, i.e., what, when, who, where, and why. We then conduct a comprehensive survey of explainable recommendation itself in terms of three aspects: 1) We provide a chronological research line of explanations in recommender systems, including the user study approaches in the early years, as well as the more recent model-based approaches. 2) We provide a taxonomy for explainable recommendation algorithms, including user-based, item-based, model-based, and post-model explanations. 3) We summarize the application of explainable recommendation in different recommendation tasks, including product recommendation, social recommendation, POI recommendation, etc. We devote a chapter to discuss the explanation perspectives in the broader IR and machine learning settings, as well as their relationship with explainable recommendation research. We end the survey by discussing potential future research directions to promote the explainable recommendation research area. 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. Introduction Explainable Recommendation A Historical Overview Classification of the Methods Explainability and Effectiveness Explainability and Interpretability How to Read the Survey Information Source for Explanations Relevant User or Item Explanation Feature-based Explanation Opinion-based Explanation Sentence Explanation Visual Explanation Social Explanation Summary Explainable Recommendation Models Overview of Machine Learning for Recommendation Factorization Models for Explainable Recommendation Topic Modeling for Explainable Recommendation Graph-based Models for Explainable Recommendation Deep Learning for Explainable Recommendation Knowledge Graph-based Explainable Recommendation Rule Mining for Explainable Recommendation Model Agnostic and Post Hoc Explainable Recommendation Summary Evaluation of Explainable Recommendation User Study Online Evaluation Offline Evaluation Qualitative Evaluation by Case Study Summary Explainable Recommendation in Different Applications Explainable E-commerce Recommendation Explainable Point-of-Interest Recommendation Explainable Social Recommendation Explainable Multimedia Recommendation Other Explainable Recommendation Applications Summary Open Directions and New Perspectives Methods and New Applications Evaluation and User Behavior Analysis Explanation for Broader Impacts Cognitive Science Foundations Conclusions Acknowledgements References