Utilizing a sizable dataset from ConvAbuse, the researchers explore a number of machine learning models, including Logistic Regression and Random Forest, to identify and classify hate speech. TextBlob, VADER, and Hugging Face’s Transformers Library are some of the sentiment analysis tools used to evaluate the emotional tone of online comments. It is assessed to what extent these tools are able to accurately detect attitudes linked to hate speech. The accuracy and reliability of detection systems are significantly improved by integrating hu-man-centered approaches, which require understanding linguistic subtleties and context. The results demonstrate that combining sentiment analysis with human-centered machine learning techniques can lead to a more successful framework for identifying hate speech. This technique reduces false positives and negatives, increases detection accuracy, and offers a more balanced moderation system.


By author

Leave a Reply

Your email address will not be published. Required fields are marked *