Online reviews explain differences in coastal and inland tourists' satisfaction.

To achieve a comprehensive understanding of the factors influencing tourist satisfaction, there has recently been an increasing interest in the information provided by online reviews. In this regard, a rather unexplored issue concerns the causal relationship between topics and emotions expressed by consumers in the written text and their overall quality assessment given through a rating system. This study aims to contribute to filling this gap by investigating whether there are differences between coastal and inland Sardinian hotels in the topics and emotions expressed by online reviewers and how both affect customer satisfaction. To this end, we apply the new TOBIAS method which models the impact of topics, moods, and emotions contained in reviews on the level of satisfaction expressed by customers through the number of stars. The novelty of this method is that it combines natural language processing and causal inference to explain the customer's overall quality rating.