Anomaly Detection with Joint Representation Learning of Content and Connection
This addresses the issue of information manipulation on social media for political contexts, but it is incremental as it builds on existing anomaly detection methods by combining content and network features.
The paper tackled the problem of detecting anomalous behavior on social media by jointly embedding user content and follower networks to identify densely connected user groups, and applied this method to the 2019 Canadian Elections to find troll-like behavior in local politics.
Social media sites are becoming a key factor in politics. These platforms are easy to manipulate for the purpose of distorting information space to confuse and distract voters. Past works to identify disruptive patterns are mostly focused on analyzing the content of tweets. In this study, we jointly embed the information from both user posted content as well as a user's follower network, to detect groups of densely connected users in an unsupervised fashion. We then investigate these dense sub-blocks of users to flag anomalous behavior. In our experiments, we study the tweets related to the upcoming 2019 Canadian Elections, and observe a set of densely-connected users engaging in local politics in different provinces, and exhibiting troll-like behavior.