Exploring Hate Speech Classification in Low-Resource Languages: A Comprehensive Review

Yadav, Sargam and Kaushik, Abhishek and McDaid, Kevin Exploring Hate Speech Classification in Low-Resource Languages: A Comprehensive Review. In: Detecting Hate Speech in Human and AI-Generated Content: Techniques, Bias Mitigation, and Ethical Considerations. IGI Global Scientific Publishing.

PDF - Draft Version Restricted to Registered users only Download (889kB)

Abstract

The widespread adoption of social media has profoundly impacted the lives of individuals, businesses, and governments, fostering greater connectivity. However, a byproduct of online anonymity is that individuals are more willing to display aggression. This hateful behavior can negatively impact groups and discourage their participation in digital conversations. This chapter surveys recent and pertinent literature that utilizes Natural Language Processing (NLP) techniques to automatically detect online hate speech, including studies that explore model explainability with Explainable Artificial Intelligence (XAI). Furthermore, the chapter reviews shared tasks and challenges that have contributed towards advancing research in hate speech detection. The findings suggest that despite the recent strides made in the development of Artificial Intelligence (AI) models for hate speech detection, the problem requires further examination, creation of benchmark datasets, and examination of explainable methodologies, particularly in the identification of misogynistic content.

Item Type:	Book Section
Subjects:	Computer Science > Computer Software
Research Centres:	Regulated Software Research Centre
Depositing User:	Sargam Yadav
Date Deposited:	24 Mar 2026 16:51
Last Modified:	24 Mar 2026 16:51
License:	Creative Commons: Attribution-Noncommercial-Share Alike 3.0
URI:	https://eprints.dkit.ie/id/eprint/1035

Actions (login required)

View Item

Downloads