Advanced Fake News Detection: Multi-Lingual Analysis and Image Forgery Detection Integration

The advent of the internet has brought about both positive changes and some critical issues. One critical issue is the spread of fake news, which leads to misinterpretation of events, threats to social integrity, and just gives rise to chaos. To tackle this problem, an efficient system is required which can detect fake news effectively. The proposed system introduces a multi-functional fake news detection system. The system makes the use of Gradient Boosting Classifier and Decision Tree Classifier algorithms to predict the authenticity of textual news articles with high accuracy. Furthermore, it integrates a novel feature to analyze the authenticity of images accompanying news articles, using Error Level Analysis (ELA) combined with Convolutional Neural Networks (CNN) to detect signs of image forgery. To enhance versatility and to reduce linguistic challenges, the system can analyze and classifying news articles in both English and Hindi, addressing the diversity of a country like India. The implementation involves preprocessing, feature extraction, and model training, ensuring reliability and robustness. This work contributes to the development of a comprehensive tool that can effectively classify text and images for authenticity, making it a valuable resource in combating the spread of fake news.