Text classification techniques used to facilitate cyber terrorism investigation
The rising of computer violence, such as Distributed Denial of Service (DDoS), web vandalism, and cyber bullying become more serious issues when they are politically motivated and intentionally conducted to generate fear in society. These kinds of activities are categorized as cyber terrorism. As the number of such cases increase, the availability of information regarding these actions is required to facilitate experts in investigating cyber terrorism. Meanwhile, web mining is one of significant technologies applied to extract information from the Web. In this case, web mining facilitates data acquisition related to cyber terrorism information from the Web. This research aims to create text classification technique based upon number of occurrences of certain relevant words in the term of Cyber Terrorism. This research compared the result of accuracy of several algorithms including Na├¤ve Bayes, Nearest Neighbor, Support Vector Machine (SVM), Decision Tree, and Multilayer Perceptron Neural Network. The result shows that SVM outperform by achieving 100% of accuracy. According to this result, it concludes the excellent performance of SVM in handling high dimensional of data.
B00731 | (wh) | Available |
No other version available