D-XCB: Data-independent Debiasing for Fair and Accurate Transformer-based Cyberbullying Detection

arXiv:2402.16458v1 Announce Type: new
Abstract: Swear words are a common proxy to collect datasets with cyberbullying incidents. Our focus is on measuring and mitigating biases derived from spurious associations between swear words and incidents occurring as a result of such data collection strategies. After demonstrating and quantifying these biases, we introduce ID-XCB, the first data-independent debiasing technique that combines adversarial training, bias constraints and debias fine-tuning approach aimed at alleviating model attention to bias-inducing words without impacting overall model performance. …

abstract arxiv biases collection cs.cl cyberbullying data data collection datasets detection fair focus independent measuring strategies transformer type words