A text analytics approach for online retailing service improvement: Evidence from Twitter

Abstract

The purpose of this study is to identify the customers' primary topics of concern regarding online retail brands that are shared among Twitter users. This study collects tweets associated with five leading UK online retailers covering the period from Black Friday to Christmas and New Year's sales. We use a combination of text analytical approaches including topic modelling, sentiment analysis, and network analysis to analyse the tweets. Through the analysis, we identify that delivery, product and customer service are among the most-discussed topics on Twitter. We also highlight the areas that receive the most negative customer sentiments such as delivery and customer service. Interestingly, we also identify emerging topics such as online engagement and in-store experience that are not captured by the existing literature on online retailing. Through a network analysis, we underscore the relationships among those important topics. This study derives insights on how well the leading online retail brands are performing and how their products and services are perceived by their customers. These insights can help businesses understand customers better and enable them to convert the information into meaningful knowledge to improve their business performance. The study offers a novel approach of transforming social media data into useful knowledge about online retailing. The incorporation of three analytical approaches offers insights for researchers to understand the hidden content behind the large collections of unstructured bodies of text, and this information can be used to improve online retailing services and reach out to customers.

Revealing industry challenge and business response to Covid-19: a text mining approach

“…To examine the relationship between the topics identified by the STM analysis, we conduct a network analysis which has been applied in a number of content analysis studies for modelling the connections between discussion topics and categories based on words co-occurrence (e.g., Ibrahim & Wang, 2019). Network analysis is defined as a set of techniques to depict the relations among entities and can help researchers to analyse the structures that emerge from the recurrence of these relations (Chiesi, 2015).…”

Online User Review Analysis for Product Evaluation and Improvement

“…As a consequence, we get the R 2 of 0.537 and MAPE of 9.9% and compared to Zhao et al [39] that, likewise using online reviews to predict user satisfaction (rating) and getting 0.385 R 2 , we believe our product evaluation indicator system can accurately reflect users' evaluation on the product. For other studies aiming at extract improvement ideas from online reviews [40,41], our approach consider the resource limitation of manufacturers and thus analyze the priority of different product attributes for improvement. Therefore, the improvement ideas acquired are the most urgent and important for product improvement based on our algorithm and have more practical meanings.…”

Utilization of text mining as a big data analysis tool for food science and nutrition

“…It has proven that digital text data analytics is a cost‐effect approach for restaurants to gain quality improvement ideas from customers. In particular, topic modeling, sentiment analysis, and network analysis are popular text analysis methods used in mining customer comments (Ibrahim & Wang, ).…”