ReSpam: A Novel Reputation Based Mechanism of Defending against Tag Spam in Social Computing

Abstract

Defending against spam in tagging system is a very challenging task. This paper presents ReSpam, a novel reputation based mechanism of defending against tag spam in tagging systems. In ReSpam, timing behaviors and voting methods are introduced to defend tag spam. Each user has a global reputation which can increase or decrease after some judgement given bythe tagging system. When the system finds that the time between logging and posting is too short or the time between opening a webpage and posting a tag is too short, the reputations of all the users who post a tag of that kind will decrease. For a uncertain tag, the system requests some users to help to judge the quality of that uncertain tag. If the feedback shows that lots of users regard that tag as spam, all the users who post a tag of that kind will find their reputations lower than before. Otherwise, those users' reputations will increase. The advantage of ReSpam is its simple rationale and less computing compared to pairwise reputation based mechanism such as SpamClean and DSpam. The system ranks search result by the average reputation of annotators of each result. Experimental results show ReSpam can effectively resist tag spam and work better than some existing tag search schemes.