Is a bunch of words enough to detect disagreement in hateful content?

AbstractThe complexity of the annotation process when adopting crowdsourcing platforms for labeling hateful content can be linked to the presence of textual constituents that can be ambiguous, misinterpreted, or characterized by a reduced surrounding context. In this paper, we address the problem of perspectivism in hateful speech by leveraging contextualized embedding representation of their constituents and weighted probability functions. The effectiveness of the proposed approach is assessed using four datasets provided for the SemEval 2023 Task 11 shared task. The results emphasize that a few elements can serve as a proxy to identify sentences that may be perceived differently by multiple readers, without the need of necessarily exploiting complex Large Language Models.