Randomized tag recommendation in social networks and classification of spam posts

Tag recommendation is an integral part of any bookmarking application. With the growing popularity in Web 2.0 usage, recommending tags is of utmost importance in enabling a user to perform bookmarking easily. An issue that most recommendation systems do not consider is that users have a tendency to choose from tags that are suggested to them, which might bias the true popular rankings of tags. In this paper we consider the problem of tag recommendation for bookmarks based on user feedback. We propose an approach for automatic tag recommendation by using a suggestion set and discuss a randomized suggestion rule for learning the true popular tags. As our algorithm depends on the frequency of tag suggestions, the action of spammers and malicious users may result in skewed ranking of tags for a bookmark. Hence, there arises a need to identify malicious users and spam posts to reinforce the efficiency of our algorithm because spammers can easily mislead a system. We have proposed an approach for classifying spammers based on tagging history of users. Our approach basically estimates the probability of a user being a spammer by analyzing previous posts and tags. Our analysis on a dataset of a popular bookmarking site shows that the proposed method is effective in suggesting the true popular tags and identifying spammers.