Database for storing and analyzing tweets posted during disasters

Abstract

In the last few decades, we have witnessed many natural disasters that have shaken the nations across the world. Millions of people have lost their lives, cities have been destroyed, people have gone homeless, injured and their lives have been affected. Sometimes hours or even days after a disaster, people are still stuck in the disaster sites, powerless, homeless and without food, as the rescue teams do not always get information about people in need in a timely manner. Whenever there is a natural disaster like a hurricane or an earthquake, people start tweeting about it. Most of the tweets are posted by users who are in the disaster sites, and may contain information about victims of the disaster: where they are and what the problem is, in what areas the rescue teams should work or focus on, or if someone needs special help. Such information can be very useful for the response teams, which can leverage this information in the recovery or rescue process. However, rescue team are faced with an information overload problem, due to the large number of tweets they need to sift through. To help with this issue, computational approaches can be used to analyze and prioritize information that may be useful to the rescue teams.

In this project, we have crawled tweets related to natural disasters, and extracted useful information in CSV files. Then, we have designed and developed a database to store the tweets. The design of the database is such that it will help us to query and gain information about a natural disaster. We have also performed some statistical analysis, such as deriving word clouds of the tweets posted during natural disasters. The analysis shows the areas where the users who post tweet about disaster are highly concerned. The word cloud analysis can help in comparing multiple natural disasters to understand patterns that are common or specific to disasters in terms of how Twitter users talk about them.