Fake News Detection: Leveraging Natural Language Processing and Machine Learning for Reliable Information Verification

This dissertation details the creation and assessment of a machine learning algorithm designed to identify fake news utilizing Natural Language Processing (NLP) methods. The research employs several machines learning models, including Long Short-Term Memory (LSTM) and other deep learning techniques, to detect and classify misleading information. Data is sourced from a variety of platforms, such as social media and online news outlets, to compile a thorough dataset. The data is pre-processed to eliminate noise, address missing values, and extract essential features through techniques like tokenization, stop-word removal, and lemmatization. The performance of the models is evaluated using key metrics such as accuracy, precision, recall, and F1-score. The results indicate that LSTM models surpass traditional methods, offering more precise and trustworthy fake news detection. Additionally, the research investigates hybrid models that integrate multiple machine learning strategies to enhance classification accuracy. These results underscore the promise of AI-driven fake news detection systems in addressing misinformation, especially in political settings, while also demonstrating their usefulness for real-time content filtering on social media platforms.