Detecting Spammers on Social Networks Based on Extreme Learning Machine.

Within past few years, the number of online social networks increased strongly and social networks has become a major way for online communications. Twitter is one of them that allocates a large number of users to communicate and attracts online users. Unfortunately, this popularity also absorb a large amount of spammers who continuously expose malicious behavior (e.g., post messages containing commercial URLs, following a larger amount of users, etc.), leading to misunderstanding and disturbance on users social activities. Given that spammers are increasing on Twitter, the success of real time search services and mining tools relies at the ability to distinguish valuable tweets from the spam ones.This kind of spam can contribute to reduce the value of real time search services unless mechanisms to fight and stop spammers can be found. In this paper we used a labeled dataset from twitter and classify them with Extreme learning machine and other data mining algorithms, finally we could decrease the response time to 0.017 second and achieved 83.33% accuracy for detecting spammers as non spammers

Keywords:

Social Networks , Spammer Detection , Extreme Learning Machine , Data Mining Algorithms