Purpose
This study aims to explore the hidden connectivity among words by semantic network analysis, further identify salient factors accounting for customer satisfaction of coffee shops through analysis of online reviews and, finally, examine the moderating effect of business types of coffee shops on customer satisfaction.
Design/methodology/approach
Two typical major procedures of big data analytics in the hospitality industry were adopted in this research: one is data collection and the other is data analysis. In terms of data analysis, frequency analysis with text mining, semantic network analysis, CONCOR analysis for clustering and quantitative analysis with dummy variables were performed to dig new insights from online customer reviews both qualitatively and quantitatively.
Findings
Different factors were extracted from online customer reviews contributing to customer satisfaction or dissatisfaction, and among these factors, the brand-new factor “Sales event” was examined to be significantly associated with customer satisfaction. In addition, the moderating effect of business types on the relationship between “Value for money” and customer satisfaction was verified, indicating differences between customers from different types of coffee shops.
Research limitations/implications
The present study broadened the research directions of coffee shops by adopting online customer reviews through relative analytics. New dimensions such as “Sales event” and detailed categorization of “Coffee quality”, “Interior” and “Physical environment” were revealed, indicating that even new cognition could be generated with new data source and analytical methods. The industry professionals could develop their decision-making based on information from online reviews.
Originality/value
The present study used online reviews to understand coffee shop costumer experience and satisfaction through a set of analytical methods. The textual reviews and numeric reviews were concerned simultaneously to unearth qualitative perception and quantitative data information for customers of coffee shops.