A Systematic Web Mining Based Approach for Forecasting Terrorism

As the volume of accessed information on the World Wide Web is enormous, there might be various web environments of terrorist groups that might comprise various types of information like images, voice, texts which might be a danger for entire web costumers. Thus, a superior technique to detect wicked and non-wicked information is necessitated. This research study provides web sites’ users a solution to prevent them from terrorist threats via developing an intelligent system to recognize the useful contents. The main aim of this study is to understand the behavior of the system, and determine the best solution for securing the susceptible users, state and society. The Naive Bayes approach (NB) and K-Nearest Neighbor (K-NN) algorithms are investigated on various Kurdish-Sorani data sets as an alternative for replacing traditional approaches. In regards to precision, the Naive Bayes algorithm demonstrates promising outcomes. The results of this paper will show that the Naive Bays technique generates greater Kappa Statistics and excellent precision compared with K-Nearest Neighbors.