How social media can contribute during disaster events? Case study of Chennai floods 2015

Abstract

During the time of crisis millions of microblogs are generated in the social media. Specifically large amount of tweet messages are posted by the users. These can be opinion oriented, sentimental tweets or ones that contribute important information. The latter kind of tweets plays a vital role in decision making during a crisis situation. These types of tweets are referred as situation awareness tweets. Extraction of situation awareness information from Twitter is a non-trivial task as the vocabulary used usually is not formal and presence of short hand words for ease of writing reduces the readability of tweets. Crowdsourcing of data during such a disaster can aid in the task of decision making. In this paper, we propose a technique of extracting situation awareness information using concepts of semi-supervised machine learning along with creating interactive map to locate the vulnerable areas during a disaster.