SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of "Subjectivity" and "Identity Terms"
This work addresses bias in content moderation systems for social media platforms, offering an incremental improvement over existing methods.
The paper tackled bias in toxic comment classification models, which often produce false positives for non-toxic comments containing identity terms like 'Muslim' or 'black', by proposing SS-BERT, a model that leverages subjectivity levels and identity term presence, resulting in improvements of up to 2.43% in F1 score over BERT and 1.91% over a state-of-the-art bias-mitigation model.
Toxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as "Muslim" and "black". Such bias is commonly reflected in false-positive predictions, i.e. non-toxic comments with identity terms. In this work, we propose a novel approach to tackle such bias in toxic comment classification, leveraging the notion of subjectivity level of a comment and the presence of identity terms. We hypothesize that when a comment is made about a group of people that is characterized by an identity term, the likelihood of that comment being toxic is associated with the subjectivity level of the comment, i.e. the extent to which the comment conveys personal feelings and opinions. Building upon the BERT model, we propose a new structure that is able to leverage these features, and thoroughly evaluate our model on 4 datasets of varying sizes and representing different social media platforms. The results show that our model can consistently outperform BERT and a SOTA model devised to address identity term bias in a different way, with a maximum improvement in F1 of 2.43% and 1.91% respectively.