Identifying video spammers in online social networks

Abstract

In many video social networks, including YouTube, users are permitted to post video responses to other users' videos. Such a response can be legitimate or can be a video response spam, which is a video response whose content is not related to the topic being discussed. Malicious users may post video response spam for several reasons, including increase the popularity of a video, marketing advertisements, distribute pornography, or simply pollute the system.In this paper we consider the problem of detecting video spammers. We first construct a large test collection of YouTube users, and manually classify them as either legitimate users or spammers. We then devise a number of attributes of video users and their social behavior which could potentially be used to detect spammers. Employing these attributes, we apply machine learning to provide a heuristic for classifying an arbitrary video as either legitimate or spam. The machine learning algorithm is trained with our test collection. We then show that our approach succeeds at detecting much of the spam while only falsely classifying a small percentage of the legitimate videos as spam. Our results highlight the most important attributes for video response spam detection.

Detecting spammers and content promoters in online video social networks

“…Additionally, we preliminarily approached this problem by creating a small test collection composed of spammers and legitimate users, and applying a binary classification strategy to detect spammers [6]. The present work builds on this preliminary effort by providing a much more thorough, richer and solid investigation of the feasibility and tradeoffs in detecting video polluters in online video sharing systems, considering a much larger test collection, a richer set of user attributes, as well as different types of malicious and opportunistic behaviors.…”

An Improved Mechanism Using J48 Classifiers for Spam Filtering

“…Benevenuto et al [7] provided a heuristic for classifying an arbitrary video as legitimate or spam. In the proposed method, the dataset of Youtube users is collected and manually classified to be spam or legitimate.…”

Identifying fraudulently promoted online videos

“…The former topic has been discussed in [5] where the authors investigate the types and duration of activities performed by users on popular social network sites. The latter topic was partially covered by Benevuto et al in [6], [7] as well as Hendrickson et al in [8] where the authors looked at the video responses (i.e. videos uploaded in response to another video) on YouTube and tried to identify videos and misbehaving user profiles that pollute YouTube by uploading unrelated video responses.…”