Classification of fake news using multi-layer perceptron

"Fake News (FNs) is defined as a made-up story to deceive or mislead." The problem of FNs spread widely in recent years, especially on social media such Facebook, Twitter, and other sources like webs blogs. It has become significant society result changing people's ideas opinions about the direction this news. In paper, detection can be proposed by using Term Frequency-Inverse Document Frequency (TF-IDF) features extraction, Multi-Layer perceptron (MLP) algorithm classifier. Two phases (feed-forward back-propagation) are used with three-layers, which (input layer, one hidden output layer). After running our dataset, classification accuracy achieved equals 95.47%.