How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have

arXiv:2305.14081v2 Announce Type: replace
Abstract: Due to the broad range of social media platforms, the requirements of abusive language detection systems are varied and ever-changing. Already a large set of annotated corpora with different properties and label sets were created, such as hate or misogyny detection, but the form and targets of abusive speech are constantly evolving. Since, the annotation of new corpora is expensive, in this work we leverage datasets we already have, covering a wide range of tasks …

abstract arxiv cs.cl data detection ever few-shot language media platforms requirements set social social media social media platforms solve systems type