Author Gender Identification from Arabic Youtube Comments
Jihad Zahir, Youssef Mehdi Oukaja, HAJAR MOHAMED MOUSANNIF · 2019
In this paper, we present a machine learning based approach to gender identification from Arabic text in Youtube comments. The proposed methodology handles dialectal Arabic, addresses the limitations of state-of-the art approaches and achieves an accuracy of 92% and an average precision of 98%.