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.