Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection

TL;DR

This thesis investigates how bias in NLP models affects hate speech detection, highlighting the importance of integrating social sciences to improve bias measurement and mitigation.

Contribution

It provides a comprehensive analysis of bias impacts on hate speech detection from explainability, stereotyping, and fairness perspectives, emphasizing interdisciplinary approaches.

Findings

Bias in NLP models affects hate speech detection across multiple dimensions

Incorporating social sciences is essential for effective bias mitigation

Current bias measurement methods are limited without social science insights

Abstract

This paper is a summary of the work done in my PhD thesis. Where I investigate the impact of bias in NLP models on the task of hate speech detection from three perspectives: explainability, offensive stereotyping bias, and fairness. Then, I discuss the main takeaways from my thesis and how they can benefit the broader NLP community. Finally, I discuss important future research directions. The findings of my thesis suggest that the bias in NLP models impacts the task of hate speech detection from all three perspectives. And that unless we start incorporating social sciences in studying bias in NLP models, we will not effectively overcome the current limitations of measuring and mitigating bias in NLP models.