Sentiment Analysis for Hateful Content on Social Media

Hate speech in social media has become a significant concern in today's age, making detecting and analyzing hate speech accurately an area of high importance. Sentiment analysis can aid in automatically detecting hate speech and quantifying its severity, providing valuable insights to social media platforms and law enforcement agencies in taking appropriate action against hate speech. This study aimed to develop and evaluate a deep learning model for hate speech detection and scoring on social media platforms. LSTM and CNN deep learning classifiers were employed and evaluated using standard metrics such as Test Accuracy, Precision, Recall, and F1 Score. The LSTM model performed the best, with 82.67% test accuracy. For regression, seven machine learning models and three deep learning models were tested, with a 3-layer deep learning regressor achieving the best score of 91.28%. The results suggest that deep learning models can effectively detect and categorize hate speech on social media platforms.