Sentiment Analysis of Twitter Users Over Time: The Case of the Boston Bombing Tragedy

Social Network Services (SNS), for example Twitter, play a significant role in the way people share their emotions about specific events. Emotions can spread via SNS and can spur people's future actions. Therefore, during extreme events, disaster response agencies need to manage emotions appropriately via SNS. In this research, we investigate the Twitter verse associated with an event - the Boston Bombing context. We focus on tweets in the context of hazard-describing keywords (Explosion, Bomb), important event timelines, and the related changes in emotions over time. We compare the results with a corpus of tweets collected at the same time that are not associated with the above hazard- describing keywords. A sentiment analysis shows anger was the most strongly expressed emotion in both groups. However, there were statistical differences in Anxiety and Sadness among the two groups over time.