Ex-ThaiHate: A Generative Multi-task Framework for Sentiment and Emotion Aware Hate Speech Detection with Explanation in Thai

Abstract

Social media platforms (SMPs) have both positive and negative impacts on users in diverse societies. One of the adverse effects of SMPs is the usage of hate and offensive language, which not only fosters prejudice but also harms the vulnerable. Additionally, a person's sentiment and emotional state heavily influence the intended content of any social media post. Despite extensive research being conducted to detect online hate speech in English, there is a lack of similar studies on low-resource languages such as Thai. The recent enactment of laws like the ``right to explanations'' in the General Data Protection Regulation has stimulated the development of interpretable models rather than solely focusing on performance. Motivated by this, we created the first benchmark hate speech corpus, called Ex-ThaiHate, in the Thai language. Each post is annotated with four labels, namely hate, sentiment, emotion, and rationales (explainability), which specify the phrases that are responsible for annotating the post as hate. In order to investigate the effect of sentiment and emotional information on detecting hate speech posts, we propose a unified generative framework called GenX, which redefines this multi-task problem as a text-to-text generation task to simultaneously solve four tasks: hate-speech identification, rationale detection, sentiment, and emotion detection. Our extensive experiments demonstrate that GenX significantly outperforms all baselines and state-of-the-art models, thereby highlighting its effectiveness in detecting hate speech and identifying the rationales in low-resource languages.