Abstract

This paper aims to analyze online customers’ reviews and gain insight into customer satisfaction factors drawn from a big user-generated content of US online retailers. This user-generated content has become more insightful, especially in the CO VID-19 era as the result of a rapid increase in online shopping. This study uses a big textual data of 5 340 786 online reviews which was collected from the platform bizratesurvey.com. The study focuses on individual customers’ reviews of 839 US online retailers. Word frequency analysis and latent dirichlet allocation methods were used to process the data. The results revealed three main topics related to the ease of use, product, and delivery that were mentioned by highly satisfied customers of US online retailers. The authors have labeled the topics properly by considering at least twenty of the most probable words in each topic. The results provide a pathway for online retail executives for enhancing shopping experiences through the ease of purchasing, the improvement of product quality and delivery for customers. Practitioners can replicate the process of data analysis fulfilled in this study in order to monitor customer feedback. The findings also provide a new way of using big textual data from customer reviews in further studies.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call