Semi-Supervised Machine Learning for Analyzing COVID-19 Related Twitter Data for Asian Hate Speech
Caitlin Richardson, Sandeep Shah, Xiaohong Yuan · 2022
The COVID-19 pandemic left a lot of people sick, tired, and frustrated. Many people expressed their feelings on social media through comments and posts. Detecting hate speech on social media is important to help reduce the spread of racist comments. Machine learning algorithms can be used to classify hate speech. In our experiments, we implement semi-supervised machine learning algorithms to classify Twitter data. We used a count vectorizer as the feature and a support vector machine (SVM) classifier to classify COVID-19 related Twitter data while changing the amount of labeled data available. We found that self-training semi-supervised machine learning has similar effectiveness to supervised learning when there is significantly less training data available.