This study aims to decode guest satisfaction with peer-to-peer accommodations by analyzing the relationship between guests’ sentiment and online ratings and examining how analytical thinking and authenticity influence this relationship. Based on reviews of 4602 Airbnb listings in San Francisco, we empirically find that positive
(negative) sentiment is linked to a high (low) rating. We further show that this link is stronger when guests manifest a higher extent of analytical thinking and authenticity. Both Tobit and ordered logit models yield consistent estimation results, showing the robustness of our findings. Our study contributes to the tourism and
hospitality literature by theoretically explaining the association between sentiment and ratings. In addition, this paper enriches our knowledge regarding the trustworthiness of Airbnb ratings.