Explainable Recommendation: A Survey and New Perspectives

Abstract

Explainable recommendation attempts to develop models that generate not only high-quality recommendations but also intuitive explanations. The explanations may either be post-hoc or directly come from an explainable model (also called interpretable or transparent model in some contexts). Explainable recommendation 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. It also facilitates system designers for better system debugging. In recent years, a large number of explainable recommendation approaches -especially model-based methods -have been proposed and applied in real-world systems.In this survey, we provide a comprehensive review for the explainable recommendation research. We first highlight 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 on three perspectives: 1) We provide a chronological research timeline of explainable recommendation, including user study approaches in the early years and more recent model-based approaches. 2) We provide a two-dimensional taxonomy to classify existing explainable recommendation research: one dimension is the information source (or display style) of the explanations, and the other dimension is the algorithmic mechanism to generate explainable recommendations. 3) We summarize how explainable recommendation applies to different recommendation tasks, such as product recommendation, social recommendation, and POI recommendation.We also devote a section to discuss the explanation perspectives in broader IR and AI/ML research. We end the survey by discussing potential future directions to promote the explainable recommendation research area and beyond.Explainable recommendation refers to personalized recommendation algorithms that address the problem of why -they not only provide users or system designers with recommendation results, but also explanations to clarify why such items are recommended. In this way, it helps to improve the transparency, persuasiveness, effectiveness, trustworthiness, and user satisfaction of the recommendation systems. It also facilitates system designers to diagnose, debug, and refine the recommendation algorithm.To highlight the position of explainable recommendation in the recommender system research area, we classify personalized recommendation with a broad conceptual taxonomy. Specifically, personalized recommendation research can be classified into the 5W problemswhen, where, who, what, and why, corresponding to time-aware recommendation (when), location-based recommendation (where), social recommendation (who), application-aware re...

Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation

“…Explainable Recommendation. Explainable recommendation has also attracted a lot of attention in recent years [43]. Early approaches attempt to use topic models to generate intuitive explanations for recommendation results, e.g., [20,23,34].…”

Meta Decision Trees for Explainable Recommendation Systems

“…In the field of RS, there have been various studies (Tintarev & Masthoff, 2007;Zhang & Chen, 2018) showing that equipping recommendations with personalized explanations helps to improve the system's persuasiveness and the users trust in it. In recent years, collaborative filtering methods, in particular those utilizing deep learning models (Hartford et al, 2018;Berg et al, 2017;Zheng et al, 2016), have improved recommendation performances, yet, the black box nature of deep learning models and the latent space used in collaborative filtering, make these models hard to explain.…”

Ethics of Food Recommender Applications

“…• Lack of explainability: In addition the score it gives to products, Yuka also recommends an alternative product in the case a given product has fared below an overall score of 50. However, despite the growing interest in eXplainable AI and its impact on enhancing user trust and acceptability [5], as well as explainable and fair recommender systems [28,49], Yuka does not explain why a particular product is chosen as an alternative. Conspicuously, the recommended alternatives are not ranked by their score but other factors such as 'product availability' (which is not a real-time assessment based on, for instance, location or real supermarket supplies) but another constant assigned to a product.…”