Classification of radical web text using a composite-based method

The spread of terrorism and extremism activities on the Internet has created the need for intelligence gathering via Web and real-time monitoring of potential websites for extremist activities. However, the manual classification for such contents is practically difficult and time-consuming. In response to this challenge, an automated classification system called Composite technique was developed. This is a computational framework that explores the combination of both semantics and syntactic features of textual contents of a Web page. We implemented the framework on a set of extremist Web pages - a dataset that has been subjected to a manual classification process. Thereby, we developed a classification model on the data using the J48 decision algorithm, to generate a measure of how well each page can be classified into their appropriate classes. The classification result obtained from our method when compared with other states of the art, indicated a 96% success rate overall in classifying Web pages when matched against the manual classification.