Cyberbullying Detection With Fairness Constraints

Cyberbullying is a widespread adverse phenomenon among online social interactions in today's digital society. While numerous computational studies focus on enhancing the cyberbullying detection performance of machine learning algorithms, proposed models tend to carry and reinforce unintended biases. In this study, we try answer research question “Can mitigate bias by guiding model training with fairness constraints?” For purpose, propose scheme that can employ constraints validate our approach different datasets. We demonstrate various types biases be successfully mitigated without impairing quality. believe work contributes pursuit unbiased, transparent, ethical solutions for cyber-social health.