Identification of Natural Disaster Affected Area Precise Location Based on Tweets
B. Premamayudu1, P. Subbarao2, Koduganti Venkata Rao3
1B.Premamayudu, Department of Information Technology, Vignan Foundation for Science Technology and Research Deemed Be University, Vadlamudi, Guntur (Andhra Pradesh), India.
2P.Subbarao, Department of Information Technology, Vignan Foundation for Science Technology and Research Deemed Be University, Vadlamudi, Guntur (Andhra Pradesh), India.
3Koduganti Venkata Rao, Department of Computer Science and Engineering, Vignan’s Institute of Information Technology, Gajuwaka, Visakhaptnam (Andhra Pradesh), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 119-123 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3414048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Twitter is an “in the moment” platform designed for customers to post tweets about any event, which reports any major event including natural disasters. Hence, social media creates volumes of data on an event. Therefore, during the time of natural disaster like tsunami, earthquake, floods, landside etc., people of that area require information in those situations to enable relief operations to save many lives. This paper presents the identification of natural disaster affected area based on twitter tweets using Geoparsing to mark the places of disaster on a world map. In the proposed mechanism, longitude and latitude location of twitter message can extracted to map geographical coordinates in GoogleMapPlotter. The source of the geographical coordinates in real time is twitter messages collected based on the keyword and timeline. We can parse real time collected twitter messages for the natural disaster effected areas and locations. The collected tweets and their location information will help us to identify the exact place of disaster event. These tweets location information is stored in database or saved in CSV format to create the dataframe in python pandas. Further, the visualization is performed on the prepared dataframe using GoogleMapPlotter. This visualization is helpful for the disaster relief operations and estimates the severity of the natural disaster. The truthiness of the user tweets is evaluated using sentiment analysis for decision making.
Keyword: Twitter, Tweets, Dataframe, Pandas, Python, Googlemapplotter, Sentiment Analysis.
Scope of the Article: Natural Language Processing