Online hate speech propagation is a complex issue, deeply influenced by both the perpetrator and the target’s cultural, historical, and so- cietal contexts. Consequently, developing a universally robust hate speech classifier for di- verse social media texts remains a challenging and unsolved task. The lack of mechanisms to track the spread and severity of hate speech further complicates the formulation of effective solutions. In response to this, to monitor hate speech in Indonesia during the recent 2024 presidential election, we have employed advanced Natural Language Processing (NLP) technologies to create an improved hate speech classifier tailored for a narrower subset of texts; specifically, texts that target vulnerable groups that have historically been the targets of hate speech in Indonesia. Our focus is on texts that mention six vulnerable minority groups in Indonesia: Shia, Ahmadiyyah, Christians, LGBTQ+, Indonesian Chinese, and people with disabilities, and Jews.
Publication: Proceedings of Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations
Co-authors: Derry Wijaya, Monash University.