Comparative Analysis of Hate Speech Detection: Traditional vs. Deep Learning Approaches

Detecting hate speech on social media poses a significant challenge, especially in distinguishing it from offensive language, as learning-based models often struggle due to nuanced differences between them, which leads to frequent misclassifications of hate speech instances, with most research focusing on refining hate speech detection methods. Thus, this paper seeks to know if traditional learning-based methods should still be used, considering the perceived advantages of deep learning in this domain. This is done by investigating advancements in hate speech detection. It involves the utilization of deep learning-based models for detailed hate speech detection tasks and compares the results with those obtained from traditional learning-based baseline models through multidimensional aspect analysis. By considering various aspects to gain a comprehensive understanding, we can discern the strengths and weaknesses in current state-of-the-art techniques. Our research findings reveal the performance of traditional learning-based hate speech detection outperforms that of deep learning-based methods. While acknowledging the potential demonstrated by deep learning methodologies, this study emphasizes the significance of traditional machine learning approaches in effectively addressing hate speech detection tasks. It advocates for a balanced perspective, highlighting that dismissing the capabilities of traditional methods in favor of emerging deep learning-based techniques may not consistently yield the most effective results.