Machine Learning Approach to Determine the Impact of Hate Speech Based on Public Opinions

Abstract

In an era dominated by online communication, the prevalence of hate speech has emerged as a significant societal concern. This paper presents a comprehensive study utilizing machine learning techniques to assess the detrimental effects of hate speech on public opinions. Utilizing a varied dataset encompassing public sentiments, we utilize advanced machine learning algorithms to categorize the adverse effects of hate speech. This study employs a combination of quantitative, qualitative, and experimental research methodologies. The experimentation phase involved training and testing the models using Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF). The resulting model demonstrates high accuracy and precision, with LR achieving (0.96, 0.97), D T showing (0.99, 100), and RF exhibiting (100, 100). Our findings reveal compelling insights into the negative impact of hate s peech. By classifying the negative repercussions, this research not only advances our understanding of online discourse but also provides a valuable foundation for the development of strategies to combat hate speech and cultivate a more inclusive digital environment.