Causal Inference for Early Detection of Pathogenic Social Media Accounts
This work addresses the challenge of detecting harmful accounts like terrorist supporters early to prevent viral spread, but it appears incremental as it builds on existing causal inference methods applied to a specific domain.
The paper tackles the problem of early detection of pathogenic social media accounts by using causal inference to identify them based on user action logs, resulting in a scheme that groups users by causality scores and classifies accounts without needing network structure or content.
Pathogenic social media accounts such as terrorist supporters exploit communities of supporters for conducting attacks on social media. Early detection of PSM accounts is crucial as they are likely to be key users in making a harmful message "viral". This paper overviews my recent doctoral work on utilizing causal inference to identify PSM accounts within a short time frame around their activity. The proposed scheme (1) assigns time-decay causality scores to users, (2) applies a community detection-based algorithm to group of users sharing similar causality scores and finally (3) deploys a classification algorithm to classify accounts. Unlike existing techniques that require network structure, cascade path, or content, our scheme relies solely on action log of users.