Explainable Recommendation: A Survey and New Perspectives

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 helpsendation systems. It also facilitates system design to improve the transparency, persuasiveness, effectiveness, trustworthiness, and…

• NS
  National Science Foundation
• SA
  Science and Technology Facilities Council

  Awards: ST/I000976/1, ST/P000525/1, ST/L00061X/1, ST/J001465/1, ST/L006529/1, ST/L000652/1, ST/H002391/1, ST/H001581/1, ST/R000484/1, ST/M003574/1, ST/F007159/1, PP/E001149/1