Explainable Recommendation: A Survey and New Perspectives
By Yongfeng Zhang, Xu Chen. 2018
1,163 citations recorded by the source corpus.
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. 2) We provide a two-dimensional taxonomy to classify existing explainable recommendation research. 3) We summarize how explainable recommendation applies to different recommendation tasks. We also devote a chapter 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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Safety, Robustness & Interpretability, Recommender Systems
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In Information Systems
In Safety, Robustness & Interpretability
- Riccardo Guidotti
- Dino Pedreschi
- Fosca Giannotti
- Krisztian Balog
- Filip Radlinski
- Shushan Arakelyan
- Xiangnan He
- Christian Walter Peter Omlin
In Recommender Systems
Citations in the corpus
- Reinforcement Knowledge Graph Reasoning for Explainable Recommendation (2019, background): “However, researchers have noticed the difficulty of explaining the recommendation results in latent factor or latent representation models, making explainable recommendation [33, 34] an important research problem for the community.”
- Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2022, background): “to the application user being shown a wrong recommendation [62].”
- The FacT: Taming Latent Factor Models for Explainability with Factorization Trees (2019, background): “ the opaque nature of most deployed recommendation algorithms, such as latent factor models [11], eagerly calls for transparency, i.e., explaining how/why the customized result is presented to a user [20, 34, 38, 39]. Previous research has shown that explanations help users make more accurate decisi”
- Towards Knowledge-Based Recommender Dialog System (2019, background): “Besides accuracy, explainability is also an important aspect when evaluating recommender systems (Zhang et al., 2014; Zhang and Chen, 2018; Wang et al., 2018b).”
- Learning over Knowledge-Base Embeddings for Recommendation (2018, background): “users and items for recommendation. Even though many studies have applied neural techniques for recommender systems [26–28], none of the previous work has leveraged KBE for explainable recommendation [1]. However, we will show that a great advantage of learning KBEs is to generate very straight forw”
- A Survey on the Fairness of Recommender Systems (2022, background): “What are the causes of unfairness? Explainability is crucial for recommender systems as it can improve the persuasiveness of recommendations, increase user satisfaction, and enhance the transparency of the whole system [109].”
- DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification (2020, background): “Intrinsic explainability (Shu et al., 2019; He et al., 2015; Zhang and Chen, 2018) is achieved by constructing self-explanatory models that incorporate explainability directly into their structures, which requires to build fully interpretable models for clearly expressing the explainable process.”
- A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “The focus of explainable recommender systems is not only to produce accurate recommendation results but to generate persuasive explanations for how and why the item is recommended to a specific user [118, 184, 236].”
- Deep Item-based Collaborative Filtering for Top-N Recommendation (2018, background): “lanation mechanism: because the item is similar to which item you liked before. Such explanation is more concreteand more acceptable by users than “because similar users also like it” provided by UCF [46]. By ease on online recommendation, the composability of ICF in user preference modeling —i.e., ”
- Reinforcement Learning based Recommender Systems: A Survey (2021, background): “Incorporating knowledge graphs into RSs can boost recommendation accuracy and explainability [38].”
- A Reinforcement Learning Framework for Explainable Recommendation (2018, background): “This increases the explainability of the recommendation model [15].”
- AliCoCo: Alibaba E-commerce Cognitive Concept Net (2020, background): “While explainable recommendation attracts much research attention recently [33], most existing works are not practical enough for industry systems, since they are either too complicated (based on NLG [8, 32]), or too trivial (e.”
- Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “are survey papers focusing on certain cutting-edge aspects in recommender systems, such as the bias issues and debiasing methods [24], explainability/interpretability [244], evaluation issues [177], and novel methods that leverage deep neural networks [242, 220, 221], knowledge graphs [61], or reinf”
- Benchmarking and survey of explanation methods for black box models (2021, background): “Finally, we highlight that the literature reviews related to explainability are focused not just on ML and AI but also on social studies (Miller 2019; Byrne 2019), recommendation systems (Zhang and Chen 2020), model-agents(Anjomshoae et al.”
- Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives (2021, background): “Specifically, the explanations could justify the reasons for recommending each energy efficiency act [263].”
- When large language models meet personalization: perspectives of challenges and opportunities (2023, neutral): “explanations, which can be broadly categorized into itembased, user-based, and attribute-based explanations[113].”
- Multistakeholder recommendation: Survey and research directions (2020, background): “It has been shown that explanations can enhance users’ likelihood of adopting a given recommendation (Zhang and Chen 2018).”
- Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, background): “Explainable recommendation has also attracted a lot of attention in recent years [43].”