Explaining customer ratings and recommendations by combining qualitative and quantitative user generated contents

This study explores the qualitative and quantitative used generated contents to find what explains customer ratings and recommendations disentangling them based on user-generated content collected from an online airlines review website, and explored how such relationship strengths change over various business contexts.

Abstract

Customer ratings and recommendations are not only important performance indicators for businesses alone, but they act as an important source of information for potential ‘uninformed’ customers. In this study, we explore the qualitative and quantitative used generated contents to find what explains customer ratings and recommendations disentangling them based on user-generated content collected from an online airlines review website. We performed text mining to find the overall sentiment and emotions expressed by customers in general, and focused on sentiments expressed over various service aspects. We found the relationships of such sentiments and emotions expressed in textual reviews and the relationships of quantitative ratings given to various core and augmented service aspects with the customer ratings and recommendation decisions. Then, we explored how such relationship strengths change over various business contexts. The results yielded important theoretical contributions to extant literature on service evaluations, construal levels, online reviews and recommendations etc. Moreover, we believe that our results would be useful for practitioners who may want to use the methodology in order to create quick and meaningful insights combining both qualitative and quantitative user generated contents, thereby helping them in service design, communication design and post-purchase strategies. As a matter of fact, such insights could also help potential travelers with an aggregated view of service quality, which in turn could help them in purchase decision making.