CSEIT195249 | Received : 01 March 2019 | Accepted : 10 March 2019 | March-April -2019 [ 5 (2) : 176-181 ]
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
© 2019 IJSRCSEIT | Volume 5 | Issue 2 | ISSN : 2456-3307
DOI : https://doi.org/10.32628/CSEIT195249
176
Disaster Reporting and Alert System Using Tweets in a Social
Media
Dr. P. Tamije Selvy, V. Suriya Prakash, S. Shriram, N. Vimalesh
Department of Computer Science, Sri Krishna College of Technology Kovaipudur, Coimbatore, Tamil Nadu,
India
ABSTRACT
The number of Social Media users have increased rapidly these days and a lot of valuable as well as non
valuable information is shared in the social which is capable of reaching many people in a short period of time
and hence the valuable information that are shared in the social media can be used for many types of analysis.
In this paper the tweets that are shared in the name of a disaster is taken and then a alert system is build. This
alert system gives alert to the users after checking the received data with the centralized database. This paper
also gives a comparative study on the algorithm used in extracting the data from the social media which gives
us the accuracy rate of different algorithm that can be used for text mining.
Keywords : Text Mining, Disaster, Twitter, Tweets
I. INTRODUCTION
These days micro-blogging websites are being used
by many people around the world. Micro-blogging
website is a website where the users can post
messages, images, etc., Twitter is an example of a
micro-blogging service. As per the survey at the end
of 2018 there are nearly 321 million active users in
twitter. There are a lot of information that is
exchanged in twitter daily and this data can be used
for a lot of good reasons. In this paper the data that is
collected from the model that represents twitter and
the data is used for giving an alert for the users and
then also to give an overall report by using the
number of tweets that are posted from a specific
location. Nowadays due to a lot of messages that are
posted on twitter twitter can’t monitor the tweets
accordingly and hence a lot of spam messages are
posted and also many terrorists organizations misuse
the micro-blogging sites for the transfer of attack
messages. Twitter is used for the transfer of messages
on different terrorist attacks by the ISIS jihadis[1].
Hundreds of ISIS-supporting accounts sent tweets
with location metadata embedded[2]. This model
which also uses a microblogging application which
has similar features like twitter. The dynamic data is
generated by various users for a particular event, this
generated data is pretty much helpful to generate a
report for the particular event. This model which
highly concentrates on disaster events. The data
generated by the user in the time of disaster is pretty
much valid to know the immediate cause of the
disaster. This model extracts the data generated by
various user and which examine those data with a
algorithm which coordinates the valid data regarding
the particular disaster, this valid data are used to find
the aftermath or consequences of the occurred
disaster which also programmed in a way to sent the
alert message to the particular user who belongs to
the disaster area. The results are however produced as
a graphical representation.