Implementing a Hybrid method For Fake News Detection

Abstract

The increasing consumption of news on social media platforms is mainly due to its cheap and attractive nature and it’s capable of spreading the fake news. The spread of fake news has negative effects on society. Some people make it up to get attention or gain political gain. Machine learning and deep learning techniques have been developed to detect fake news. However, they tend to generate inaccurate reports. To detect fake news, we used a Hybrid model that combines SVM and Naive Bayes (NBSVM) framework. It was able to classify the news with an accuracy of 84.85%. This model was tested and trained on a fake news challenge dataset. We used various evaluation metrics (precision, recall, F1- measure, etc.) to measure the model's efficiency