Characterizing and Detecting Hateful Users on Twitter

Abstract

Most current approaches to characterize and detect hate speech focus on \textit{content} posted in Online Social Networks. They face shortcomings to collect and annotate hateful speech due to the incompleteness and noisiness of OSN text and the subjectivity of hate speech. These limitations are often aided with constraints that oversimplify the problem, such as considering only tweets containing hate-related words. In this work we partially address these issues by shifting the focus towards \textit{users}. We develop and employ a robust methodology to collect and annotate hateful users which does not depend directly on lexicon and where the users are annotated given their entire profile. This results in a sample of Twitter's retweet graph containing $100,386$ users, out of which $4,972$ were annotated. We also collect the users who were banned in the three months that followed the data collection. We show that hateful users differ from normal ones in terms of their activity patterns, word usage and as well as network structure. We obtain similar results comparing the neighbors of hateful vs. neighbors of normal users and also suspended users vs. active users, increasing the robustness of our analysis. We observe that hateful users are densely connected, and thus formulate the hate speech detection problem as a task of semi-supervised learning over a graph, exploiting the network of connections on Twitter. We find that a node embedding algorithm, which exploits the graph structure, outperforms content-based approaches for the detection of both hateful ($95\%$ AUC vs $88\%$ AUC) and suspended users ($93\%$ AUC vs $88\%$ AUC). Altogether, we present a user-centric view of hate speech, paving the way for better detection and understanding of this relevant and challenging issue.

arXiv commentThis is an extended version of the homonymous short paper to be presented at ICWSM-18. arXiv admin note: text overlap with arXiv:1801.00317

Cited by in corpus (20)

• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
• Social Media Polarization and Echo Chambers in the Context of COVID-19: Case Study
• The Structure of Toxic Conversations on Twitter
• Analyzing the hate and counter speech accounts on Twitter
• Tackling Online Abuse: A Survey of Automated Abuse Detection Methods
• Deep Learning Models for Multilingual Hate Speech Detection
• Hate begets Hate: A Temporal Study of Hate Speech
• Automatically Detecting Cyberbullying Comments on Online Game Forums
• Characterizing Twitter Users Who Engage in Adversarial Interactions against Political Candidates
• A Survey on Multimodal Disinformation Detection
• Does Terrorism Trigger Online Hate Speech? On the Association of Events and Time Series
• Online Hate: Behavioural Dynamics and Relationship with Misinformation
• Multimodal Learning for Hateful Memes Detection
• Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop
• Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
• Towards Time-Aware Context-Aware Deep Trust Prediction in Online Social Networks
• Predicting Anti-Asian Hateful Users on Twitter during COVID-19
• Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability
• dictNN: A Dictionary-Enhanced CNN Approach for Classifying Hate Speech on Twitter
• Deep Unified Multimodal Embeddings for Understanding both Content and Users in Social Media Networks