Novel DeepLearning based sentimental approach to identifying the fake news in social networking media based smart application

Abstract

The increasing spread of fake news on social networks is a pressing issue, with severe potential harm to individuals, communities, and society. To tackle this problem, we propose a novel deep learning-based approach that utilizes convolution neural networks (CNNs) and restricted Boltzmann machines (RBMs) to capture the intricate relationships between the textual content of news articles and their underlying sentiment. Our approach consists of a comprehensive pipeline that involves data pre-processing, feature extraction, and classification using a combination of CNNs and RBMs. Our approach is not limited to social networks and can be extended to other domains, such as e-commerce platforms, insurance and financial industries, politics, and national security. It has the potential to identify and mitigate the harmful effects of fake news by detecting fake reviews and comments on e-commerce platforms, identifying fraudulent claims in insurance and financial industries, and identifying propaganda and disinformation campaigns in politics and national security for smart applications.

Keywords

• Deep learning
• Sentimental approach
• Identifying
• Counterfeit files
• Social network
• Smart application