Mail_Alert: Online Suspicious URL Detection of Tweets from Twitter Public Timeline

Twitter, a famous social networking site where thousands of users use it to tweet to the world, is prone to spam, phishing, and malware distribution. Tweets are the atomic building blocks of Twitter, 140-character status updates with additional associated metadata. People tweet for a variety of reasons about a multitude of topics. Traditional spam detection scheme for twitter are ineffective against feature fabrications or consume much time and resources. Conventional suspicious URL detection schemes utilize several features including lexical features of URLs, URL redirection, HTML content, and dynamic behavior. However, evading techniques such as time-based evasion and crawler evasion exist. In this paper, we propose a suspicious URL detection system for Twitter in which numerous tweets from the Twitter public timeline is collected and dynamic trained classifier is been built to classify among suspicious and the real ones. Timelines are collections of Tweets, ordered with the most recent first. Evaluation results show that our classifier accurately and efficiently detects suspicious URLs. A near real-time system for classifying suspicious URLs in the Twitter stream. In this paper I propose to block the malicious URLs and provide mail alert for malicious URLs occur in the twitter stream. Keywords—Twitter, Trained SVM classifier, share URLs, mail_alert Spoorthi K et al, International Journal of Computer Science and Mobile Computing, Vol.3 Issue.4, April2014, pg. 817-824 © 2014, IJCSMC All Rights Reserved 818