The truth is increasingly hard to discern in the world we know today. Extreme political polarization has become a result of twisted facts, inaccurate statistics, and the dramatization of events. My research is an effort to tackle the pressing issue of fake news on the internet. Fake news is misinformation that is released online under the guise of reliable news headlines. This can be misleading to targeted individuals who are exposed to false information, and can potentially sway public opinion to extremes. Thus, in this paper, I attempt to leverage Machine Learning to classify an article's headline text as true or fake news. With the help of Dr. Parsa Akbari of Cambridge University, I track two models, RoBERTa and LSTM-RNN, and compare their progress from their respective F1 Scores to reach a conclusion on which model is best suited for NLP analysis. Ultimately, my model can be implemented on search engines such as Google to flag websites as false if they contain misinformation, which can later be verified by an expert, in hopes of ensuring the validity of online content.