Fake News Detection Using Naïve Bayes and Support Vector Machine
Vasireddy Sneha, Velaga Sravani, V. S. S. Bala Tripura Sathvika, Banoth Venu Kumar, A. Jagan · 2023
Social media platforms have revolutionised how people engage with the outside world by allowing people to voice their thoughts and exchange information on a variety of topics that interest them. However, because social media is so widely used, information spreads quickly among thousands of users, giving it the perfect environment for the fast spread of false information. The alarming rise of false news presents major concerns to both users and the nation, demanding prompt action. On a national and personal level, the potential harm that misinformation can do calls for serious thought and preventive action. Online fake news identification has garnered substantial research interest, yet the results of past endeavors, particularly using the naive Bayes classifier, have yielded suboptimal performance. In response, this work aims to go deeper into the topic and address the constraints of the naive Bayes classifier by investigating techniques to improve its efficiency. To efficiently identify fake news on social media, we provide a machine learning-based technique that makes use of Naïve Bayes and Support Vector Machine classifiers. Our main goal is to provide users with a tool that enables them to separate significant information from false information and determine the reliability of news stories they come across online.