The growth of hate speech and online harassment on social media platforms makes the creation of efficient solutions to address this persistent problem necessary. A promising method for locating and monitoring hate speech in social media is sentiment analysis, a computational tool that auto detects and assesses the emotional tone of text. To empower platforms to take preventative action against the spread of hate speech, this work addresses the use of sentiment analysis as a tool to identify and analyse hate speech. In this paper, we focus on hate detection in textual content and use machine learning algorithms to categorize and measure hateful content. This approach can assist in content moderation, enhance user safety, and foster a more positive online environment. To improve the precision and dependability of sentiment analysis algorithms, issues including context sensitivity and changing language patterns must be addressed. The AI-enabled discussion forum incorporates an innovative design that addresses hate speech discussions through machine learning algorithms and active tagging to improve accuracy.