Explainable Identification of Hate Speech towards Islam using Graph Neural Networks
Azmine Toushik Wasi
TL;DR
This work targets Islam-directed hate speech on online platforms by formulating detection as a graph-based problem where each utterance is a node and edges encode contextual similarity. A multi-layer Graph Neural Network with a linear projection, neighborhood aggregation, and an attention-based layer predicts hate-speech targets, while GNNExplainer provides explanations via subgraphs and feature masks. On the HateXplain Islam-focused subset, the proposed XG-HSI variants outperform strong baselines, with XG-HSI-BERT achieving up to 0.751 accuracy and 0.747 Macro F1, demonstrating both high performance and interpretability. The approach advances safe, explainable moderation by leveraging graph structure and pretrained embeddings to capture nuanced context in Islamophobic content.
Abstract
Islamophobic language on online platforms fosters intolerance, making detection and elimination crucial for promoting harmony. Traditional hate speech detection models rely on NLP techniques like tokenization, part-of-speech tagging, and encoder-decoder models. However, Graph Neural Networks (GNNs), with their ability to utilize relationships between data points, offer more effective detection and greater explainability. In this work, we represent speeches as nodes and connect them with edges based on their context and similarity to develop the graph. This study introduces a novel paradigm using GNNs to identify and explain hate speech towards Islam. Our model leverages GNNs to understand the context and patterns of hate speech by connecting texts via pretrained NLP-generated word embeddings, achieving state-of-the-art performance and enhancing detection accuracy while providing valuable explanations. This highlights the potential of GNNs in combating online hate speech and fostering a safer, more inclusive online environment.