A multitask learning framework for leveraging subjectivity of annotators to identify misogyny

TL;DR

A multitask learning approach that leverages the subjectivity of this task to enhance the performance of the misogyny identification systems and highlights the importance of embracing diverse perspectives to build effective online moderation systems.

Abstract

Identifying misogyny using artificial intelligence is a form of combating online toxicity against women. However, the subjective nature of interpreting misogyny poses a significant challenge to model the phenomenon. In this paper, we propose a multitask learning approach that leverages the subjectivity of this task to enhance the performance of the misogyny identification systems. We incorporated diverse perspectives from annotators in our model design, considering gender and age across six profile groups, and conducted extensive experiments and error analysis using two language models to validate our four alternative designs of the multitask learning technique to identify misogynistic content in English tweets. The results demonstrate that incorporating various viewpoints enhances the language models' ability to interpret different forms of misogyny. This research advances content moderation and highlights the importance of embracing diverse perspectives to build effective online moderation systems.

Figures (2)

• Figure 1: General architecture design for incorporating the annotator profile perspectives as auxiliary tasks to support the learning of the hard label as the main task
• Figure 2: Comparison of Single-task learning and Multi-task learning architectures when applying the variation of freezing versus updating the model parameters