THREAT: A Large Annotated Corpus for Detection of Violent Threats

Understanding, detecting, moderating and in extreme cases deleting hateful comments in online discussions and social media are well-known challenges. In this paper we present a dataset consisting of a total of around 30 000 sentences from around 10 000 YouTube comments. Each sentence is manually annotated as either being a violent threat or not. Violent threats is the most extreme form of hateful communication and is of particular importance from an online radicalization and national security perspective. This is the first publicly available dataset with such an annotation. The dataset can further be useful to develop automatic moderation tools or may even be useful from a social science perspective for analyzing the characteristics of online threats and how hateful discussions evolve.