A Comparative Study of Various Machine Learning (ML) Approaches for Fake News Detection in Web-based Applications
摘要
The development of fake news detection and intervention methods is a result of the exponential spread of false news and its impact on justice, democracy, and public confidence. People’s trust in the government, news media, news stories, social media, etc. has decreased as a result of widespread fake news. Hence, fake news has become a crucial problem in our society. In this chapter we have presented a comparative examination of detecting fake news. We have defined the negative behavior of bogus news and introduced detection methods. Many of such methods rely on identifying content and context aspects that suggest misrepresentation. We also looked at existing datasets that have been employed to categorize bogus news. Finally, we have suggested possible research avenues by applying various machine learning-based classification algorithms and analyzed bogus news in terms of various performance parameters like accuracy, precision, recall, and F1 score.