Visualizing Explainable Touristic Recommendations: An Interactive Approach

Abstract

AbstractPersonalized recommendations have played a vital role in tourism, serving various purposes, ranging from an improved visitor experience to addressing sustainability issues. However, research shows that recommendations are more likely to be accepted by visitors if they are comprehensible and appeal to the visitors’ common sense. This highlights the importance of explainable recommendations that, according to a previously specified goal, explain an algorithm’s inference process, generate trust among visitors, or educate visitors by making them aware of sustainability practices. Based on this motivation, our paper proposes a visual, interactive approach to exploring recommendation explanations tailored to tourism. Agnostic to the underlying recommendation algorithm and the defined explainability goal, our approach leverages knowledge graphs to generate model-specific and post-hoc explanations. We demonstrate and evaluate our approach based on a prototypical dashboard implementing our concept. Following the results of our evaluation, our dashboard helps explain recommendations of arbitrary models, even in complex scenarios.