Twitter emergency response system during flood-related disaster
by Jagrati Singh; Anil Kumar Singh
International Journal of Emergency Management (IJEM), Vol. 17, No. 2, 2021

Abstract: The ubiquity of mobile, laptop and social media platforms such as Twitter is accelerating the information flow around the world. This can be useful to handle emergencies during a natural disaster, as victims can share on-the-spot situations and officials can put the solutions on the same platform. We proposed a new emergency response system, aimed at providing help to victims during flood-related disasters based on their tweets. The system consists of three modules: The first module identifies high priority tweets that are asking for help. In the second module, each high priority tweet is given an emergency score based on the victim's location information to help them at an early stage. We proposed a new natural language technique named LDFT (location detection from a tweet) to infer the mentioned locations in the text of the tweet. The third module applies the DBSCAN clustering algorithm on high scoring tweets and displays the obtained clusters on Google Maps to visualise the hot-spot areas easily. The proposed disaster response system works well, with its maximum accuracy of 78%, and location prediction accuracy of 75%.

Online publication date: Tue, 17-May-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Emergency Management (IJEM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com