A multitask learning framework for leveraging subjectivity of annotators to identify misogyny
This research addresses the problem of online toxicity against women for content moderation systems, representing an incremental improvement by leveraging subjectivity in annotation.
The paper tackled the challenge of identifying misogyny in online content by proposing a multitask learning framework that incorporates diverse annotator perspectives based on gender and age, and it demonstrated that this approach enhances language models' ability to interpret different forms of misogyny in English tweets.
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.