Deep learning representations in automatic misogyny identification: What do we gain and what do we miss?

In this paper, we address the problem of automatic misogyny identification focusing on understanding the representation capabilities of widely adopted embeddings and addressing the problem of unintended bias. The proposed framework, grounded on Sentence Embeddings and Multi-Objective Bayesian Optimization, has been validated on an Italian dataset. We highlight capabilities and weaknesses related to the use of pre-trained language, as well as the contribution of Bayesian Optimization for mitigating the problem of biased predictions.