Gender-based Cyberbullying Detection for Under-resourced Bangla Language

The present study explores the detection of gender discrimination based cyberbullying in under-resourced Bangla language. While being spoken by 230 million people globally and being rich in diversity, the Bengali language lacks computational models and annotated resources for cyberbullying detection. To address this, we created GenDisc, a corpus of Bangla Facebook comments featuring gender-based cyberbullying. This study also presents a framework for cyberbullying detection. In our proposed approach, we used four different models to train a gender-based discriminatory text classifier, followed by an ensembling technique on those four models. Then we compared the individual prediction accuracies with the ensembled prediction accuracy. While training the dataset, we followed the stratified k-fold cross validation technique. We demonstrated that integrating gender-based discrimination variables improve a classifier’s capacity to discriminate against cyberbullying. Our evaluations yielded an accuracy of 68% in gender-based speech detection during cross-validation tests.