Analyzing the sentiment correlation between regular tweets and retweets

• Published in: Social network analysis and mining 2020-12, Vol.10 (1), p.13, Article 13
• Main Authors: Chen, Jundong, Hossain, Md Shafaeat, Zhang, Huan
• Format: Article
• Language: English
• Subjects: Applications of Graph Theory and Complex Networks; Computer Science; Correlation coefficients; Data collection; Data Mining and Knowledge Discovery; Earthquakes; Economics; Game Theory; Humanities; Information dissemination; Law; Machine learning; Measurement methods; Methodology of the Social Sciences; Original Paper; Sentiment analysis; Social and Behav. Sciences; Social networks; Statistics for Social Sciences
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-020-0624-4

Retweeting is an important way of information propagation on Twitter. In this paper, we investigate the sentiment correlation between regular tweets and retweets. We anticipate our investigation sheds a light on how the sentiment of regular tweets impacts the retweets of different sentiments. We propose a method for measuring the sentiment of tweets. We categorize the Twitter users into different groups by different norms, which are the follower count, the betweenness connectivity, a combination of follower count and betweenness centrality, and the amount of tweets. Then, we calculate the sentiment correlation for different groups to examine the influential factors for retweeting a message with a certain sentiment. We find that the users with higher betweenness centrality and higher tweets amount tend to exhibit a higher sentiment correlation. The users with medium-level f o l l o w e r s _ c o u n t show the highest sentiment correlation compared to the low-level and high-level f o l l o w e r s _ c o u n t . After combining the two factors of f o l l o w e r s _ c o u n t and betweenness centrality, we discover that specifically at low-level betweenness centrality the users with medium-level f o l l o w e r s _ c o u n t have the highest sentiment correlation. Our last observation is that the difference for correlation coefficients exists between different types of users. Our study on the sentiment correlation provides instructional information for modeling information propagation in human society.