Social media plays a major role in the propagation of information during disasters. This paper mainly contains a study regarding how people of Chennai used social media especially twitter, in response to the country’s worst flood that had occurred recently. The tweets collected were analysed using machine learning algorithms such as Random Forests, Naive Bayes and Decision Tree. By comparing the performances of all the three it was found that Random Forests is the best algorithm that can be relied on, during a disaster. This paper also targeted the sources of the Twitter messages to explore the most influential users of Chennai flood.
