Title :
T - vigilant: To unmask radical attacks and halt the innocents
Author :
Prasad J. Koyande;Kavita P. Shirsat
Author_Institution :
Computer Engineering, Mumbai University, Vidyalankar Institute of Technology, VIT, India
Abstract :
Forbearance and wisdom should be the key now. The system to prevent terrorist attacks that will relay emergency alerts to all phones is set to begin. This system could warn people of terrorist strikes by text message. With the popularity of Social Networks, mostly news providers used to split their news in various social networking sites and web blogs. In India, many news groups stake their news on Twitter micro blogging service provider which provides real-nature to the system. The system is an early precursor that collects and analyzes real-time news of events such as terrorist attack, hijack, bomb blast etc. from Twitter and detects a target event. Objective behind is to ooze message to all the phones in a given area, providing them with up-to-date and accurate guidance on the specific threat and the best way to escape. Machine learning techniques were used to train the data. In order to create the instances words from each short message were consider and bag-of-words approach was used to create feature vector. The data was trained using KNN (K - Nearest Neighbor) machine learning techniques. The KNN is a typical learning algorithm based on analogy, so if category has a certain amount of the training samples which helps to guarantee the accuracy of classification. Large amount of feature will be collected for current research. The performance will speak the efficaciousness of the system.
Keywords :
"Terrorism","Twitter","Training","Supervised learning","Feature extraction","Unsupervised learning","Computers"
Conference_Titel :
Next Generation Computing Technologies (NGCT), 2015 1st International Conference on
DOI :
10.1109/NGCT.2015.7375205