Real-Time Fake News Detection Using Big Data Analytics and Deep Neural Network

In today's fast-paced world, the Internet has become a prevalent source of information for people worldwide. With the increasing use of various applications, people can get updates in real time, making access to information more convenient than ever. However, this easy access to the Internet has also led to the rise of fake news, making it difficult for individuals to differentiate between true and false information. This is where deep learning (DL) comes into play, offering a solution to identify and combat fake news. In this era of technology, DL can be a game-changer in detecting fake news and preventing potential damage to individuals and organizations. A hybrid N-gram and long short-term memory (LSTM) model improves accuracy, recall rate, and computation time, making the fake news detection process more elegant. This proposed model utilizes a classifier to classify fake news. It is based on the parallel and distributed platform, enabling it to build the DL model using big data analytics. This platform improves the training and testing time and enhances the accuracy of the proposed model. The proposed system classifies news into two categories", fake news" and "real news", while quantifying the results to develop a system that can detect fake news with high accuracy and a meager mistake rate. Integrating the deep neural network (DNN) and Spark architecture of big data makes the proposed model highly efficient, as demonstrated by the results.