IMMENSE: Inductive Multi-perspective User Classification in Social Networks

2026-08-05

AI Summary

This study addresses the urgent need for effective mechanisms to identify malicious users on social networks who disseminate discriminatory, hateful, and violent content harmful to adolescents. The authors propose a novel multi-view inductive classification approach that integrates content semantics, social relationships, and spatial information within a unified inductive learning framework—eliminating the need for model retraining when applied to new users or unseen networks. By synergistically combining natural language processing, graph neural networks, and geospatial analysis, the method achieves significantly superior performance over five state-of-the-art baselines on real-world Twitter/X datasets, demonstrating its effectiveness and practical advantages for social network monitoring.

Abstract

Online social networks increasingly expose people to users who propagate discriminatory, hateful, and violent content. Young users, in particular, are vulnerable to exposure to such content, which can have harmful psychological and social repercussions. Given the massive scale of today's social networks, in terms of both published content and number of users, there is an urgent need for effective systems to aid Law Enforcement Agencies (LEAs) in identifying and addressing users that disseminate malicious content. In this work we introduce IMMENSE, a machine learning-based method for detecting malicious social network users. Our approach adopts a hybrid classification strategy that integrates three perspectives: the semantics of the users' published content, their social relationships and their spatial information. Such contextual perspectives potentially enhance classification performance beyond text-only analysis. Importantly, IMMENSE employs an inductive learning approach, enabling it to classify previously unseen users or entire new networks without the need for costly and time-consuming model retraining procedures. Experiments carried out on a real-world Twitter/X dataset showed the superiority of IMMENSE against five state of the art competitors, confirming the benefits of its hybrid approach for effective deployment in social network monitoring systems.

Problem

• malicious user detection
• social networks
• hateful content
• online safety
• user classification

Innovation

• inductive learning
• multi-perspective classification
• malicious user detection
• social network analysis
• hybrid machine learning