Unsupervised Pathogenic Social Media Accounts Detection Without Content or Network Structure

This chapter introduces an unsupervised causality-based framework built upon the causal inference presented in Chap. 2 using label propagation. The merit of this approach is that it identifies PSM users without using network structure, cascade path information, content and user’s information which are usually hard to obtain. Results on the ISIS-A dataset discussed in the previous chapter, show that the proposed approach obtains higher precision (0.75) in identifying PSM accounts compared with the random (precision of 0.11) and existing bot detection (precision of 0.16) methods.