Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech
This addresses the challenge of explainability in detecting subtle online hate speech, which is important for researchers and practitioners in content moderation, but is incremental in exploring AI-assisted methods.
The study investigated whether ChatGPT can generate natural language explanations for implicit hate speech detection, finding that it shows potential but has limitations compared to human-written explanations.
Recent studies have alarmed that many online hate speeches are implicit. With its subtle nature, the explainability of the detection of such hateful speech has been a challenging problem. In this work, we examine whether ChatGPT can be used for providing natural language explanations (NLEs) for implicit hateful speech detection. We design our prompt to elicit concise ChatGPT-generated NLEs and conduct user studies to evaluate their qualities by comparison with human-written NLEs. We discuss the potential and limitations of ChatGPT in the context of implicit hateful speech research.