Towards travel recommendation interpretability: Disentangling tourist decision-making process via knowledge graph

•Insights into tourist decision process by a new explainable recommendation system.•Construct a knowledge graph covering the multifaceted factors in decision process.•Use knowledge graph to achieve supervised disentangled learning at multi-scales.•Restore the decision process exactly while ensuring the recommendation accuracy.•Excellent interpretability boosts the recommendation robustness on sparse dataset.