Graph-based Features for Automatic Online Abuse Detection

TL;DR

This paper explores the use of conversational network graph features derived from chat logs to detect online abuse, achieving high classification performance comparable to content-based methods.

Contribution

It introduces a graph-based feature extraction method from chat logs for abuse detection, demonstrating its effectiveness in classification tasks.

Findings

Graph features significantly improve abuse detection accuracy.

Performance comparable to content-based approaches.

Graph-based approach offers robustness against message obfuscation.

Abstract

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.