Follow spam detection based on cascaded social information

Abstract

In the last decade we have witnessed the explosive growth of online social networking services (SNSs) such as Facebook, Twitter, RenRen and LinkedIn. While SNSs provide diverse benefits for example, forstering inter-personal relationships, community formations and news propagation, they also attracted uninvited nuiance. Spammers abuse SNSs as vehicles to spread spams rapidly and widely. Spams, unsolicited or inappropriate messages, significantly impair the credibility and reliability of services. Therefore, detecting spammers has become an urgent and critical issue in SNSs. This paper deals with Follow spam in Twitter. Instead of spreading annoying messages to the public, a spammer follows (subscribes to) legitimate users, and followed a legitimate user. Based on the assumption that the online relationships of spammers are different from those of legitimate users, we proposed classification schemes that detect follow spammers. Particularly, we focused on cascaded social relations and devised two schemes, TSP-Filtering and SS-Filtering, each of which utilizes Triad Significance Profile (TSP) and Social status (SS) in a two-hop subnetwork centered at each other. We also propose an emsemble technique, Cascaded-Filtering, that combine both TSP and SS properties. Our experiments on real Twitter datasets demonstrated that the proposed three approaches are very practical. The proposed schemes are scalable because instead of analyzing the whole network, they inspect user-centered two hop social networks. Our performance study showed that proposed methods yield significantly better performance than prior scheme in terms of true positives and false positives.

Spammer Detection and Fake User Identification on Social Networks

“…Jeong et al [17] analyzed the follow spam on Twitter as an alternative of dispersion of provoking public messages, spammers follow authorized users, and followed by authorized users. Categorization techniques were proposed that are used for the detection of follow spammers.…”

Deep learning to filter SMS Spam

“…Over the years, computer scientists have proposed several machine learning models to separate Spam from Not-Spam (Abdullahi et al, 2016;AlaM et al, 2018;Chen et al, 2017;Cohen et al, 2018;Chan et al, 2015;Faulkner, 1997;Hancock, 2001;Hinde, 2002;Jeong et al, 2016;Lai, 2007;Li et al, 2017;Vorakulpipat et al, 2012;Wang & Chen, 2007). These works are not only limited to mobile phone text messages but also include Web Spam (Makkar & Kumar, 2019), Email Spam (Androutsopoulos et al, 2000;Drucker et al, 1999), and Spam on social network platforms such as Facebook, Twitter, and Sina Weibo (Ahmed et al, 2015;Chen et al, 2017;Fu et al, 2018;Lee et al, 2010;Liu et al, 2017).…”

An Internet Water Army Detection Supernetwork Model

“…In this way the spammers could be also called ''Internet water armies''. Much evidence has confirmed the negative influences of Internet water armies on the order of Internet and even the society as a whole [1], [2], [21], [22]. For instance, as Zhang and Lu [22] stated that, due to the rumors and false information posted by Internet water armies, the normal network order and social harmony and stability have been seriously disturbed.…”

“…Gillani et al [37] introduced a novel economic metric to improve the effectiveness of spam detector. By observing the relationship between different Internet water armies, Jeong et al [21] applied the Triad Significance Profile (TSP) and Social Status (SS) to detect Internet water armies. In addition, an ensemble technique was also proposed in their work.…”