Abstract
The article describes a study of identification of fake news based on natural language processing, big data analysis and deep learning technology. The developed system automatically checks the news for signs of fake news, such as the use of manipulative language, unverified sources and unreliable information. Data visualization is implemented on the basis of a friendly user interface that displays the results of news analysis in a convenient and understandable format. For news classification, a neural network was developed using LSTM bidirectional recurrent neural network (BRNN) and bidirectional layers in the model. The study demonstrates better performance of news analysis based on LSTM with 8 epochs compared to similar works with 3–4 epochs (99% vs. 85-96%). Deep learning models such as bidirectional LSTM are highly accurate in recognizing patterns in textual data, providing better results. The model showed high accuracy on the test sample, which indicates its ability to effectively recognize fake news. The confusion matrix showed that all the news items were classified correctly. The classification report confirmed high accuracy, completeness and F1 score for both classes (real and fake news).
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call