Moral framing and sentiment can affect a variety of online and offline
b...
Social stereotypes negatively impact individuals' judgements about diffe...
Majority voting and averaging are common approaches employed to resolve
...
A common practice in building NLP datasets, especially using crowd-sourc...
Bias mitigation approaches reduce models' dependence on sensitive featur...
Prediction bias in machine learning models refers to unintended model
be...
Approaches for mitigating bias in supervised models are designed to redu...
Hate speech classifiers trained on imbalanced datasets struggle to deter...
Official reports of hate crimes in the US are under-reported relative to...