DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures

arXiv:2307.16811v3 Announce Type: replace
Abstract: Public figures receive a disproportionate amount of abuse on social media, impacting their active participation in public life. Automated systems can identify abuse at scale but labelling training data is expensive, complex and potentially harmful. So, it is desirable that systems are efficient and generalisable, handling both shared and specific aspects of online abuse. We explore the dynamics of cross-group text classification in order to understand how well classifiers trained on one domain or demographic …

abstract abuse arxiv automated cs.cl cs.cy data domain identify labelling language language models life media public scale social social media systems training training data transfer type