Moralization-aware identity fusion for detecting violent radicalization in social media

Abstract

Most extremists use social media to spread radical ideologies. Existing methods for detecting violent radicalization primarily depend on superficial radicalization characteristics from user content or interactions, which fail to capture the role of morally-driven emotional shifts that underpin radicalization. These approaches overlook the dynamic convergence of moral emotions—a key facilitator of identity transformation and group allegiance. This paper proposes a novel property-specific method that incorporates moral frame, which is a systematic structure of moral reasoning rooted in foundational values such as care/harm, fairness/cheating, loyalty/betrayal, authority/subversion, and purity/degradation to model and fuse moralized identities for detecting violent radicalization. Specifically, it constructs a moral frame model integrated with user profiles to generate enhanced moralized representations, while an innovative moral identity fusion module employs heterogeneous graph neural networks to capture group moral homogeneity. A self-supervised Relational Graph Convolutional Networks (R-GCNs) clusters similar nodes to improve feature space discrimination, enabling effective violent radicalization detection through multi-module collaboration. Our experiments demonstrate significant performance across all metrics. On the moral foundation dataset, our method achieves 62.40 % accuracy, with 60.97 % macro F1 and 63.89 % weighted F1-scores, outperforming all baselines. Evaluation on datasets (340,310 tweets from Twitter; 188,358 posts from Gab) confirms the method’s detection performance. Case studies further validate its ability through moral convergence and social relationship patterns.