Access to technology and social media has revolutionized the generation and distribution of information. However, this increase in the flow of information does not necessarily translate to increased level of truthful public knowledge. Fake News has been gaining a lot of traction in recent years. Spreading fake news can lead to making uninformed decisions on political issues, health care and even create social conflict.
In this project, we focus on the hyper parameter tuning on the top three best performing models from the research paper Detection of Online Fake News Using N-Gram Analysis and Machine Learning Techniques and determining the performance of best model along with its hyper parameters on classifying news source as either Fake or Real. We want to minimize the misclassification of an actual “Fake” news as “Real” which Is why recall was considered as one of the more important model evaluation metrics.
- Hamza Luqman
- Muhammad Daud Sheikh
- Okeoghenemarho Obuareghe