A Data Mining Based Online Terrorism Detection and Prediction System

Abstract

Terrorism has grown its roots quite deep in certain parts of the world. With increasing terrorist activities, the realization of this by the researcher and the thought that it is important to drastically reduce terrorism and its spread before a certain time motivated the researcher towards this work. However, Anti-terrorist organizations have identified internet as a major source of spreading terrorism through speeches and videos; as terrorist organizations use internet to brain wash individuals and also promote terrorist activities through provocative web pages that inspire helpless people to join terrorist organizations. Thus, an efficient web data mining system to detect such web properties and flag them automatically for human review is a great benefit from the proposed system. Data mining is a technique used to mine out patterns of useful data from large data sets and make the most use of obtained results. The dataset in this consists of 18000 records and the clustering algorithm was used to mine patterns of useful data from the dataset. Web pages are made up of HTML (Hyper Text Markup Language) in various arrangements and have images, videos, etc. intermixed on a single web page. In this way we can judge web pages and check if they can be promoting terrorism. In this study, a data mining based online terrorism detection system was developed and implemented using the following programming and technological tools: PHP, Python, Jupyter Notebook, Anaconda, Django, HTML/CSS, Tableau, Python packages (Mathplotlib, Pandas and Numpy), MYSQL, and WAMP server. This system proves useful in anti-terrorism sectors and even search engines to classify web pages into various categories.