Bengali Fake News Detection Using Machine Learning and Effectiveness of Sentiment as a Feature

Fake news is one of the rising global crises. It often aims to damage the reputation of a person or entity or make money through advertising revenue. Sometimes it can become influential and can spread exceedingly fast. That is why more and more research is running in this particular sector. Bengali-speaking people are also not immune to this problem. But research on Bengali fake news is rare. Keeping this in mind, this paper experiments with machine learning (ML) techniques to detect fake news. We also incorporate sentiment as a feature to check the effect in the process. We got an highest accuracy score of 73.20% using support vector machine (SVM). Also, we show that sentiment analysis has no good prospect as a feature to detect fake news.