The Hybrid Model Combination of Deep Learning Techniques, CNN-LSTM, BERT, Feature Selection, and Stop Words to Prevent Fake News

Deep learning is a powerful and revolutionary subset of machine learning that involves training artificial neural networks to recognise patterns and predict outcomes with incredible accuracy. These neural networks are designed to mimic the human brain’s structure and can learn and improve over time through exposure to new data. This research uses other researchers’ conclusions to apply an encoding architecture to CNN-LSTM by utilising BERT. It is essential to conduct this research as it may result in the newest state-of-the-art technique for preventing fake news. It allows us to protect future generations, including adults and children, from fake news. The unique aspects of the proposed methodology and critical findings incorporate feature selection, stop words, and BERT as the encoder for CNN-LSTM. This research contributes to the field of fake news detection through the novel contribution of proposing BERT to be used as the encoder for CNN-LSTM, along with the implementation of Feature Selection and Stop Words.