Analyzing Twitter to explore perceptions of Asian restaurants

Abstract

Purpose The purpose of this paper is to use Twitter analysis to explore diner perceptions of four types of Asian restaurants (Chinese, Japanese, Korean and Thai). Design/methodology/approach Using 86,015 tweets referring to Asian restaurants, this research used text mining and sentiment analysis to find meaningful patterns, popular words and emotional states in opinions. Findings Twitter users held mingled perceptions of different types of Asian restaurants. Sentiment analysis and ANOVA showed that the average sentiment scores for Chinese restaurants was significantly lower than the other three Asian restaurants. While most positive tweets referred to food quality, many negative tweets suggested problems associated with service quality or food culture. Research limitations/implications This research provides a methodology that future researchers can use in applying social media analytics to explore major issues and extract sentiment information from text messages. Originality/value Limited research has been conducted applying social media analysis in hospitality research. This study fills a gap by using social media analytics with Twitter data to examine the Twitter users’ thoughts and emotions for four different types of Asian restaurants.