The structural topic model for online review analysis
Purpose The purpose of this study was to explore influences of review-related information on topical proportions and the pattern of word appearances in each topic (topical content) using structural topic model (STM). Design/methodology/approach For 173,607 Yelp.com reviews written in 2005-2016, STM-based topic modeling was applied with inclusion of covariates in addition to traditional statistical analyses. Findings Differences in topic prevalence and topical contents were found between certified green and non-certified restaurants. Customers’ recognition in sustainable food topics were changed over time. Research limitations/implications This study demonstrates the application of STM for the systematic analysis of a large amount of text data. Originality/value Limited study in the hospitality literature examined the influence of review-level metadata on topic and term estimation. Through topic modeling, customers’ natural responses toward green practices were identified.