Improvised Technique for Analyzing Data and Detecting Terrorist Attack Using Machine Learning Approach Based on Twitter Data

Abstract

Social media are interactive computer mediated technology that facilitates the sharing of information via virtual communities and networks. And Twitter is one of the most popular social media for social interaction and microblogging. This paper introduces an improved system model to analyze twitter data and detect terrorist attack event. In this model, a ternary search is used to find the weights of predefined keywords and the Aho-Corasick algorithm is applied to perform pattern matching and assign the weight which is the main contribution of this paper. Weights are categorized into three categories: Terror attack, Severe Terror Attack and Normal Data and the weights are used as attributes for classification. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) are two machine learning algorithms used to predict whether a terror attack happened or not. We compare the accuracy with our actual data by using confusion matrix and measure whether our result is right or wrong and the achieved result shows that the proposed model performs better.

A Machine Learning Based Framework for Collecting and Using Social Media for Real-time Terrorist Attacks Prediction

“…The most related works; using social media for terrorism prediction include [13], [14], and [15]. In [13], the NB algorithm is used, and the model performance is measured by precision, recall, and F-Measure.…”

“…Likewise, in [14], the purpose is to detect extremist-related tweets, and therefore not adequate for this project. Another related work in the area includes [15], where social media collected from Twitter (now X) are analyzed and correlated to past terrorist attacks. The difference between that research approach and ours is that we seek to predict future attacks, whereas [15] focuses on past attacks.…”

“…• Secondly, we have found in the literature that several works, including [13], [14], and [15], have also used social media as an acceptable source of information for terrorism predictions. 2) Initial Classification of social network text: Initially, we collected social network texts such as the one presented in Fig.…”

Detection and Prediction of Terrorist Activities and Threatening Events in Twitter - A Survey

“…The study concluded that fake tweets' survival rate was far longer than the real ones. An efficient and accurate model for event detection is presented in [45] which used ternary search for finding the weight of the keywords used.…”

Interoperability and Targeted Attacks on Terrorist Organizations Using Intelligent Tools from Network Science

“…This is because this kind of data are almost always classified or inappropriate for academic research [50][51][52][53][54][55]. Unlike most studies in this area, which rely on data from social media interactions [77][78][79][80][81][82][83][84][85][86][87][88][89][90][91], our work is grounded on real-world social ties among terrorists, namely physical face-to-face interactions. This kind of data is more reliable because social media interactions can be used for deliberately sharing false realities, aiming to mislead law enforcement agencies [92][93][94][95][96].…”