Automated Detection of Cyberbullying Against Women and Immigrants and Cross-domain Adaptability
This research provides an incremental improvement in automated cyberbullying detection for social media platforms, specifically targeting hate speech against women and immigrants.
This paper developed an ensemble model based on DistilBERT to detect cyberbullying against women and immigrants on Twitter, achieving F1 scores of 0.73 for hate speech classification and 0.74 for aggressiveness and target classification. The model also demonstrated cross-domain adaptability, achieving an F1 score of approximately 0.7 on external offensive language datasets.
Cyberbullying is a prevalent and growing social problem due to the surge of social media technology usage. Minorities, women, and adolescents are among the common victims of cyberbullying. Despite the advancement of NLP technologies, the automated cyberbullying detection remains challenging. This paper focuses on advancing the technology using state-of-the-art NLP techniques. We use a Twitter dataset from SemEval 2019 - Task 5(HatEval) on hate speech against women and immigrants. Our best performing ensemble model based on DistilBERT has achieved 0.73 and 0.74 of F1 score in the task of classifying hate speech (Task A) and aggressiveness and target (Task B) respectively. We adapt the ensemble model developed for Task A to classify offensive language in external datasets and achieved ~0.7 of F1 score using three benchmark datasets, enabling promising results for cross-domain adaptability. We conduct a qualitative analysis of misclassified tweets to provide insightful recommendations for future cyberbullying research.