Deep Fake BERT: Efficient Online Fake News Detection System

The newscast system has shifted from conventional print to online media platforms in the current computing era. As a result, online media platforms enable us to absorb information more quickly and with fewer editorial constraints, and false information is disseminated at an extraordinary rate and on a massive scale. Many practical algorithms for identifying fake News have recently been created, which use unidirectional text sequence analysis. News and social context-level information were encoded using sequential neural networks. As a result, a bidirectional training strategy is capable of enhancing classification. This paper proposed Deep Fake BERT, a new model for identifying bogus News in online media. The model uses a BERT-based deep learning technique by integrating multiple simultaneous modules into a single-layer DCNN with various kernel filter sizes and strides. This combination can handle ambiguity, the most challenging aspect of natural language comprehension. This approach used classification methods such as Naive Bayes, Feed Forward Neural Networks, and LSTM, and prediction results were compared. Based on the comparison, the proposed model yields a classification accuracy is 99.25% to the existing methods.