Terrorist attacks in Turkey: An evaluate of terrorist acts that occurred in 2016

Abstract

Terrorist attacks are the most significant challenging for the humankind across the world, which need the whole attention. To predict the terrorist group which is accountable for results and activities utilizing historical info is a difficult task because of the lake of detailed terrorist data. Therefore, this paper based on predicting terrorist groups responsible of attacks in TURKEY terrorist acts that occurred in 2016 by using data mining techniques is analyzing the most useful and accessible algorithms used by the machine learning systems. The typical analysis of these datasets including algorithms is implemented on the Weka tool depends upon real info represented through Global Terrorism Database (GTD) from the national consortium for the study of terrorism and responses of terrorism (START). The results of the paper show which algorithm is more convenient for a particular dataset. Tests are performed on real-life data by using Weka and also the final analysis and conclusion based on five performance steps which revealed that J48, is more accurate than Bayes Net, SVM and NB but KNN has the lowest classification accuracy although it performs well in other measures. © 2018 IEEE.