Robot restaurant experience and recommendation behaviour: based on text-mining and sentiment analysis from online reviews
Zhiyong Li, Yuan Feng, Zhenzhong Zhao
Abstract
The robot restaurant, as a brand-new and innovative catering mode, greatly relies on customer recommendations on top catering platforms. By extracting the main dimension of the robot restaurant experience and customers’ sentiment ratings in online reviews, this study investigates the impact of main dimensions and customer sentiment on recommendations. A mixed-method approach was performed to analyze online reviews from robot restaurant customers in five cities in China. Text-mining analysis identifies five main dimensions of the robot restaurant experience including food quality, intellectualization, atmosphere, value, and service quality. Regression analysis indicates that customer sentiment ratings for food quality and intellectualization significantly influence recommendations, while service quality has no effect. This study contributes to the existing tourism literature by identifying the key dimensions of the robot restaurant experience and empirically examining their relationship with actual recommendation behaviour.