Evaluating the Veracity of News Through Machine Learning Algorithms

Fake news is a growing problem in today's digital world with the increase in dependence on social media for information amongst the populace. Additionally, the proliferation of digital media platforms and the rise of user-generated content have facilitated the dissemination of false and misleading information at an unprecedented scale. This has serious consequences on individual and societal decision-making. Therefore, identifying fake news has become an important process to ensure the credibility and integrity of the consumed information. This work seeks to detect fake news using Natural Language Processing techniques and machine learning models. In this work, several Natural Language Processing techniques were used for text processing and vectorization. A labeled dataset of news articles was used to train the models, which included various models with supervised machine learning algorithms. The performance of each model was evaluated using accuracy, precision, and confusion matrix metrics. Finally, the work includes a prediction pipeline that enables users to input news articles and obtain predictions from each of the trained models. Using these methods this work achieves an accuracy of up to 91%.