CONTACT US: Contact info
|
Citation |
Singh J, Singh AK. Int. J. Emerg. Manage. 2021; 17(2): 177-193. |
|
Copyright |
(Copyright © 2021, Inderscience Publishers) |
|
DOI |
|
PMID |
unavailable |
|
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%. Language: en |