Authors: Shreyash Akole, Mansi Rakhonde, Saish Desai
Abstract: The rapid growth of online news and digital media has significantly impacted financial markets, where even a single headline can influence investor behavior. With this increasing dependence on news, ensuring the authenticity and sentiment of financial information has become more important than ever. This research presents a dual-purpose system that combines stock market news sentiment analysis with fake news detection. Our model aims to solve this by using Natural Language Processing (NLP) techniques and Machine Learning (ML) algorithms to analyze financial news, detect fake information, and suggest investment actions such as Buy, Sell, or Hold. This system uses Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) models for sentiment and authenticity analysis, ensuring reliability and accuracy. The framework empowers traders, investors, and institutions to make smarter, safer financial decisions by combining sentiment analysis and fake news detection into a single platform. Most systems only do either sentiment analysis or fake news detection. Our system does both in one place, making it more reliable. It reached 93% accuracy in sentiment analysis and 96% in fake news detection, helping users make better and safer financial decisions.
DOI:
