Detecting Communities by Sentiment Analysis of Controversial Topics

Controversial topics, particularly political topics, often provoke very different emotions among different communities. By detecting and analyzing communities formed around these controversial topics we can paint a picture of how polarized a country is and how these communities evolved over time. In this research, we made use of Internet data from Twitter, one of the most popular online social media sites, to identify a controversial topic of interest and the emotions expressed towards the topic. Communities were formed based on Twitter users’ sentiments towards the topic. In addition, the network structure of these communities was utilized to reveal those Twitter users that played important roles in their respective communities.