A Survey on Online User Aggression: Content Detection and Behavioral Analysis on Social Media

TL;DR

This survey addresses cyber-aggression as a spectrum of hostile online behavior, unifying definitions and bridging two research threads: aggression content detection and behavioral analysis of aggressors. It systematically reviews data annotation, datasets, features, algorithms, and emerging trends in detection, while separately examining qualitative and quantitative studies on what drives online aggression and its impacts. A core contribution is the proposed socio-computational integration, highlighting how sociological insights can inform feature design, modeling, and interventions, and identifying gaps in multilingual, multimodal datasets. The findings emphasize the rise of transformer-based methods, cross-lingual transfer, and the need for fair, transparent systems that consider cultural context to effectively prevent and mitigate online aggression in real-world platforms.

Abstract

The rise of social media platforms has led to an increase in cyber-aggressive behavior, encompassing a broad spectrum of hostile behavior, including cyberbullying, online harassment, and the dissemination of offensive and hate speech. These behaviors have been associated with significant societal consequences, ranging from online anonymity to real-world outcomes such as depression, suicidal tendencies, and, in some instances, offline violence. Recognizing the societal risks associated with unchecked aggressive content, this paper delves into the field of Aggression Content Detection and Behavioral Analysis of Aggressive Users, aiming to bridge the gap between disparate studies. In this paper, we analyzed the diversity of definitions and proposed a unified cyber-aggression definition. We examine the comprehensive process of Aggression Content Detection, spanning from dataset creation, feature selection and extraction, and detection algorithm development. Further, we review studies on Behavioral Analysis of Aggression that explore the influencing factors, consequences, and patterns associated with cyber-aggressive behavior. This systematic literature review is a cross-examination of content detection and behavioral analysis in the realm of cyber-aggression. The integrated investigation reveals the effectiveness of incorporating sociological insights into computational techniques for preventing cyber-aggressive behavior. Finally, the paper concludes by identifying research gaps and encouraging further progress in the unified domain of socio-computational aggressive behavior analysis.

Figures (8)

• Figure 1: Overview of our systematic literature review on cyber-aggression, introducing a new socio-computational approach to address the problem more effectively.
• Figure 2: Distribution of aggression detection datasets across OSM platforms.
• Figure 3: Analysis of language-specific datasets.
• Figure 4: Distribution analysis of features utilized in previous studies for aggression analysis.
• Figure 5: Distribution analysis of detection studies across various languages and ML algorithms.