Behind the ratings: Text mining of restaurant customers’ online reviews

Abstract

Establishing the relation between online ratings and reviews provides a potentially inexpensive and effective way for restaurants to capture quality improvement hints from customers. To this end, this study proposes an integrated approach that leverages text mining and empirical modeling to quantitatively correlate ratings with reviews. From Dianping.com (a Chinese crowd-sourced online review community), 49,080 pairs of restaurant rating and review were examined, with high-frequency words, major topics, and subtopics identified. Multilinear regression was employed to screen out the most impactful factors that influence taste, environment, and service ratings. Managerially, the idea of triggering the synergistic benefit from customer ratings and reviews is referential for market practitioners both within and beyond the catering industry.