International Research Journal of Education and Technology

Hate speech detection has become a crucial task in today's digital era due to the rapid growth of social media and online communication platforms. It poses a significant challenge as existing moderation systems struggle to effectively filter out harmful content. The need for this study arises from these limitations, necessitating more advanced and accurate solutions for identifying and addressing hate speech. The aim of this research is to develop a deep learning-based hate speech detection model that can accurately classify offensive content in text. The method involves using a labeled dataset of social media comments, employing natural language processing (NLP) techniques for feature extraction, and training a convolutional neural network (CNN) model for classification. Testing showed the proposed model achieved an accuracy of 87%, with a precision rate of 85% and recall of 88%, outperforming several existing approaches. This study highlights the integration of advanced NLP techniques with CNNs for enhancing hate speech detection capabilities. The findings imply potential implementation in real-time content moderation systems to reduce the spread of hate speech.

.

Keywords: Hate speech detection, deep learning, convolutional neural network, natural language processing, content moderation, text classification