Detecting spammers and content promoters in online video social networks

Abstract

A number of online video social networks, out of which YouTube is the most popular, provides features that allow users to post a video as a response to a discussion topic. These features open opportunities for users to introduce polluted content, or simply pollution, into the system. For instance, spammers may post an unrelated video as response to a popular one aiming at increasing the likelihood of the response being viewed by a larger number of users. Moreover, opportunistic users -promoters -may try to gain visibility to a specific video by posting a large number of (potentially unrelated) responses to boost the rank of the responded video, making it appear in the top lists maintained by the system. Content pollution may jeopardize the trust of users on the system, thus compromising its success in promoting social interactions. In spite of that, the available literature is very limited in providing a deep understanding of this problem.In this paper, we go a step further by addressing the issue of detecting video spammers and promoters. Towards that end, we manually build a test collection of real YouTube users, classifying them as spammers, promoters, and legitimates. Using our test collection, we provide a characterization of social and content attributes that may help distinguish each user class. We also investigate the feasibility of using a state-of-the-art supervised classification algorithm to detect spammers and promoters, and assess its effectiveness in our test collection. We found that our approach is able to correctly identify the majority of the promoters, misclassifying only a small percentage of legitimate users. In contrast, although we are able to detect a significant fraction of spammers, they showed to be much harder to distinguish from legitimate users.

Die Free or Live Hard? Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers

“…In addition, since spam and attacks are so rampant in online social networking sites, Koutrika et al [30] propose techniques to detect tag spam in tagging systems. Benevenuto et al [24,23] utilize machine learning techniques to identify video spammers in video social networks. Gao et al [27] present a study on detecting and characterizing social spam campaigns in Facebook.…”

Robustness of Trust and Reputation Systems: Does It Matter?

“…opinion spam) is a relatively recent research trend, so the literature is still relatively limited, but some studies show promising results. Studies include Benevenuto et al (2009) [1], Lim et al (2010) [15], Gilbert & Karrie (2010) [7], Wu et al [25,24], Ott et al (2011) [19], and Duan & Liu (2012) [5].…”

In Tags We Trust: Trust modeling in social tagging of multimedia content

“…In centralized trust systems, users' trust models are maintained by one central authority, i.e., manager, while in distributed trust systems each user maintains his/her own trust manager based on the previous interactions with other users. Distributed trust models are mainly used in P2P networks [15], while social networks usually use centralized systems (e.g., [18], [27], [24], and [30]). …”

“…Benevenuto et al [27] proposed various features for detecting spammers and promoters in the user feedback of YouTube videos. Spammers were defined as users who post an unrelated video as response to a popular one (e.g., pornographic content posted as response to a cartoon video), aiming at increasing the likelihood of the response being viewed by a larger number of users.…”

“…Since this raw data are missing ground truth for evaluation, they manually labeled a small portion of users distinguishing between legitimate users, spammers, and promoters and then evaluated their approach. The same approach for the evaluation of a trust model was followed by Benevenuto et al [27], who crawled a large-scale data set from YouTube containing more than 260,000 users and 1 million videos. Caverlee et al [30] crawled 892,000 user profiles and around 20 million relationship links from MySpace.…”