Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection
This work addresses bias in NLP models for hate speech detection, which is important for improving fairness and accuracy in social media and content moderation, but it appears incremental as it builds on existing research without introducing a new method.
The thesis investigates how bias in NLP models affects hate speech detection across explainability, offensive stereotyping, and fairness, finding that bias impacts all three areas and that integrating social sciences is crucial to overcome current limitations in measuring and mitigating bias.
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.