2025/05/01 by Prateek Kalia, Manpreet Kaur, Asha Thomas · 1 voice
Computer Science · Social Sciences · #Digital Marketing and Social Media #Sentiment Analysis and Opinion Mining #Spam and Phishing Detection
paper · pdf · doi:10.1111/ijcs.70075
openalex publication_date 2025/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/02
ABSTRACT The existing literature on human–computer interactions is rich in studies on how consumers interact with brands on social media. However, there is a gap in the research on consumers' responses to the language style of social media branded messages. Therefore, this study aims to analyze e‐retailers' Twitter (now X) posts through text analysis to identify the content attributes that are most effective in generating higher numbers of retweets. R software was used for the data extraction and analysis of 28,737 tweets posted by e‐retailers in India. We used a variety of text analysis approaches, including retweet analysis, hashtag analysis, word cloud, network analysis, and sentiment analysis to analyze the collected tweets. We observed that tweets that included questions, product names, and promotional activities attracted better retweets, and that hashtags coupled with campaigns, products, and events were dominant. On average, positively charged tweets (specifically commanded by trust) were three times more popular than negative tweets. The four most prominent themes emerging in our network analysis are help and support, contests, discounts and offers, and query handling and resolution, which induce positive intentions among online shoppers towards e‐retailers. Our findings offer insights into how e‐retailers can improve their Twitter (X) activities to engage their audiences.