Graph-based Features for Automatic Online Abuse Detection
This work addresses the challenge of automating content moderation to reduce costs, though it is incremental as it builds on prior approaches.
The paper tackled the problem of detecting abusive messages in online communities by using graph-based features from conversational networks, achieving performance comparable to existing content-based methods.
While online communities have become increasingly important over the years, the moderation of user-generated content is still performed mostly manually. Automating this task is an important step in reducing the financial cost associated with moderation, but the majority of automated approaches strictly based on message content are highly vulnerable to intentional obfuscation. In this paper, we discuss methods for extracting conversational networks based on raw multi-participant chat logs, and we study the contribution of graph features to a classification system that aims to determine if a given message is abusive. The conversational graph-based system yields unexpectedly high performance , with results comparable to those previously obtained with a content-based approach.