A Legal Approach to Hate Speech: Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task
This work addresses the challenge of automating legal judgments for hate speech, which is crucial for legal and regulatory applications, though it is incremental in adapting existing NLP methods to a specific legal context.
The authors tackled the problem of hate speech detection by operationalizing the EU's legal framework into an NLP task, showing that breaking legal assessments into sub-tasks like 'target group' and 'targeting conduct' yields better results than end-to-end approaches, with improved transparency.
We propose a 'legal approach' to hate speech detection by operationalization of the decision as to whether a post is subject to criminal law into an NLP task. Comparing existing regulatory regimes for hate speech, we base our investigation on the European Union's framework as it provides a widely applicable legal minimum standard. Accurately judging whether a post is punishable or not usually requires legal training. We show that, by breaking the legal assessment down into a series of simpler sub-decisions, even laypersons can annotate consistently. Based on a newly annotated dataset, our experiments show that directly learning an automated model of punishable content is challenging. However, learning the two sub-tasks of `target group' and `targeting conduct' instead of an end-to-end approach to punishability yields better results. Overall, our method also provides decisions that are more transparent than those of end-to-end models, which is a crucial point in legal decision-making.