Which one is more toxic? Findings from Jigsaw Rate Severity of Toxic Comments
This work addresses the need for more nuanced toxicity detection in online platforms, though it is incremental as it builds on existing methods with a new dataset.
The paper tackled the problem of measuring toxicity severity in online comments by evaluating transformer and traditional machine learning models on a Jigsaw dataset, finding that regression approaches outperform classification but with issues identified through explainability analysis.
The proliferation of online hate speech has necessitated the creation of algorithms which can detect toxicity. Most of the past research focuses on this detection as a classification task, but assigning an absolute toxicity label is often tricky. Hence, few of the past works transform the same task into a regression. This paper shows the comparative evaluation of different transformers and traditional machine learning models on a recently released toxicity severity measurement dataset by Jigsaw. We further demonstrate the issues with the model predictions using explainability analysis.