EXIST-2024: Source Intention in tweets (soft-soft)

This task aims to classify sexist tweets based on the author's intent, helping to understand the role social media plays in the emission and dissemination of sexist messages. In this task, a ternary classification is proposed: direct, reported, judgemental. This task includes a soft-soft evaluation, where the probability of each label predicted by the system is compared with the probability defined based on the annotation disagreement in the gold standard.