Improving Cyberbully Detection with User Interaction

TL;DR

This paper introduces a novel graph-based method leveraging temporal dynamics and topic coherence to improve cyberbullying detection in social media sessions, addressing limitations of previous content-only analysis.

Contribution

It proposes a unified temporal graph model and a graph neural network approach to incorporate temporal and topical interactions for better cyberbullying detection.

Findings

Enhanced detection accuracy in session-level bullying tasks

Effective modeling of temporal and topical interactions

Public release of the code for reproducibility

Abstract

Cyberbullying, identified as intended and repeated online bullying behavior, has become increasingly prevalent in the past few decades. Despite the significant progress made thus far, the focus of most existing work on cyberbullying detection lies in the independent content analysis of different comments within a social media session. We argue that such leading notions of analysis suffer from three key limitations: they overlook the temporal correlations among different comments; they only consider the content within a single comment rather than the topic coherence across comments; they remain generic and exploit limited interactions between social media users. In this work, we observe that user comments in the same session may be inherently related, e.g., discussing similar topics, and their interaction may evolve over time. We also show that modeling such topic coherence and temporal interaction are critical to capture the repetitive characteristics of bullying behavior, thus leading to better predicting performance. To achieve the goal, we first construct a unified temporal graph for each social media session. Drawing on recent advances in graph neural network, we then propose a principled graph-based approach for modeling the temporal dynamics and topic coherence throughout user interactions. We empirically evaluate the effectiveness of our approach with the tasks of session-level bullying detection and comment-level case study. Our code is released to public.