Srimayi Gupta’s scientific contributions

In an age of social media, online forums, and chats, cyberbullying is a prevalent issue. On Twitter (now X), approximately 500 million tweets are shared per day (Antonakaki et.al., 2021). It is the job of the moderators to ensure these tweets follow standard community guidelines. However, the sheer number of tweets makes it difficult to sort manually and ensure they are following protocol. Sentiment analysis and machine learning algorithms can be used to classify these texts automatically as positive or negative. Normally, these machine learning models are much more efficient and may provide higher accuracy rates in identifying hate speech in Twitter. In this paper, we are exploring the use of five classical machine learning algorithms to classify Twitter hate speech as neutral, racist, or sexist. Model performance was compared after using raw tweet data versus pre-processed tweets through data cleanup. Furthermore, we highlight two methods to deal with imbalanced datasets to improve the prediction rates. Overall, we were able to achieve a 96% accuracy in correctly classifying tweets into the different labels.