Open access
Sep 2026
Machine Learning and Deep Learning Based Classification of Profanity and Sexist Discourse in Turkish Texts
Results showed that Transformer-based models offer higher and more balanced performance than traditional machine learning models, and indicate that contextual language representations are effective in Turkish harmful content classification.
Naim Karasekreter, C. Balım, Özkan Aslan
· Black Sea Journal of Enginee... · 0 citations