A REAL TIME CHAT APPLICATION TO DETECT HATE SPEECH USING SENTIMENT ANALYSIS

ABSTRACT In recent years, the prevalence of online hate speech has raised significant concerns, particularly within academic environments where inclusivity and respect are paramount. This project presents a chat system that employs sentiment analysis to detect and mitigate hate speech in campus communications. Leveraging natural language processing (NLP) techniques, the system analyzes real-time text inputs from users, identifying harmful language patterns and emotional tones associated with hate speech. Our approach combines traditional machine learning algorithms with deep learning models to enhance detection accuracy. The system categorizes messages based on sentiment scores and predefined hate speech criteria, providing immediate feedback to users and enabling moderators to intervene when necessary. Preliminary results indicate that the chat system effectively reduces instances of hate speech while fostering a more supportive online environment. This research contributes to ongoing efforts to create safer digital spaces on campuses and emphasizes the importance of proactive measures in combating online toxicity.