Towards Perso-Arabic Urdu Language Hate Detection Using Machine Learning: A Comparative Study Based on a Large Dataset and Time-Complexity

Social media users are growing daily, with hundreds of millions of active users per month on certain networking sites. For any administrative institution, the manual method for regulating user content is challenging. There are hundreds of languages through which you can direct your attention on the web. The Urdu language is among the most widely utilized languages in the world. We have proposed a quick way of detecting the content of Urdu language hate using machine learning models. We used the open data set and manually created instances to make this investigation viable on a balanced data set. Our experimental set-up has demonstrated that support vector machine in the detection of Urdu hatred detection is 81.87% accurate. The training time, testing time, and accuracy helped us select the best model for Urdu hate detection on social media sites. We also compared the training and testing times of various methods. Additionally, we demonstrated k and stratified folding via indexing to provide a better understanding of folding in machine learning. Finally, we compared our findings to those of previously published works in the field of Urdu hate detection.