Fuzzy String Matching Algorithm for Spam Detection in Twitter

Abstract

In recent times one of the most popular Internet activity around the world is visiting online social websites. The number of users and time spent by users on these social networks is increasing exponentially. Moreover, users tend to rely on the trustworthiness of data present on these networks. But in wrong hands this trustworthiness can easily be exploited and used to spread spams. Users can easily be harassed by spam messages which waste time and can fool users to click on malicious links. Spam effects many different type of electronic communications including instant messaging, email and social networks. But due to open nature, huge user base and reliance on users for data, social networks are worst hit because of spams. To detect spams from the social networks it is desirable to find new unsupervised techniques which can save the training cost which is required in supervised techniques.

In this article we present an unsupervised, distributed and decentralized technique to detect and remove spams from social networks. We present a new technique which uses fuzzy based method to detect spams, which can detect spams even from a single message stream. To handle huge data in networks, we implement our technique to work on MapReduce platform.