Multilingual Hate Speech Detection and Counterspeech Generation: A Comprehensive Survey and Practical Guide

TL;DR

This paper offers a comprehensive survey and practical guide on multilingual hate speech detection and counterspeech generation, emphasizing challenges, recent advances, and ethical considerations to foster inclusive online safety solutions.

Contribution

It introduces a structured framework for multilingual hate speech detection and counterspeech, integrating recent datasets, models, and evaluation metrics, while addressing key challenges like data scarcity and bias.

Findings

Multilingual resources are expanding but still limited for low-resource languages.

Monolingual systems often fail in non-English and code-mixed contexts.

Ethical and cultural considerations are crucial for effective hate speech detection.

Abstract

Combating online hate speech in multilingual settings requires approaches that go beyond English-centric models and capture the cultural and linguistic diversity of global online discourse. This paper presents a comprehensive survey and practical guide to multilingual hate speech detection and counterspeech generation, integrating recent advances in natural language processing. We analyze why monolingual systems often fail in non-English and code-mixed contexts, missing implicit hate and culturally specific expressions. To address these challenges, we outline a structured three-phase framework - task design, data curation, and evaluation - drawing on state-of-the-art datasets, models, and metrics. The survey consolidates progress in multilingual resources and techniques while highlighting persistent obstacles, including data scarcity in low-resource languages, fairness and bias in system development, and the need for multimodal solutions. By bridging technical progress with ethical and cultural considerations, we provide researchers, practitioners, and policymakers with scalable guidelines for building context-aware, inclusive systems. Our roadmap contributes to advancing online safety through fairer, more effective detection and counterspeech generation across diverse linguistic environments.