The Machine Learning objective of web data mining to detect online spread of terrorism is to analyze and interpret large sets of online data to identify patterns, trends, or signals indicative of terrorist activities. By tracking communications, posts, and connections, in early detection, prevention, and response, helping authorities to safeguard security and public well-being.
In recent years, there has been a concerning rise in terrorism in specific global regions, demanding immediate action to curb its proliferation and safeguard human lives and assets. The rapid growth of terrorist activities has been facilitated by the advancement of technology, particularly the internet, which has become a powerful tool for disseminating terrorist speeches and videos. Terrorist groups exploit this digital platform to inflict harm on individuals, tarnish reputations, and recruit new members to execute criminal acts on their behalf. To address this pressing issue, web mining techniques are being explored as a means to tackle online terrorism effectively and data mining techniques are being employed in tandem to develop efficient systems. Web mining plays a crucial role, especially in dealing with unstructured data available on the web. Systems for data mining and web mining work together to mine information from diverse sources, including textual data on websites with varying data structures. However, the diverse nature of websites built on different platforms presents challenges in developing a single algorithm to read them all.
KEYWORDS:KNN.
NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.
S/W Configuration:
Operating System: Windows 7/8/10 .
Server side Script: HTML, CSS & JS.IDE : Pycharm.
Libraries Used: Numpy, IO, OS, Flask, Keras, Tensorflow
Technology: Python 3.6+.
H/W Configuration:
RAM: 8GB
Processor: I3/ Intel processor
Hard Disk: 160GB