Exploring Machine Learning Techniques for Stock Price Prediction Using Sentimental Analysis: A Comprehensive Study

Predicting stock prices is a complex task due to the unpredictable nature of financial markets. Traditional approaches often depend on historical stock data and technical indicators, which may not fully capture the impact of real-time events. With the rise of social media platforms like Twitter, public sentiment has emerged as a critical factor influencing stock prices. This study introduces a novel method for stock price prediction by combining Twitter sentiment analysis with machine learning techniques. Using Natural Language Processing (NLP) tools like VADER (Valence Aware Dictionary and Sentiment Reasoner), we analyze tweet sentiment and integrate it with historical stock data to train two ML models. The methodology includes data preprocessing, feature engineering, sentiment analysis, and model training. This research underscores the value of social media sentiment in financial forecasting and provides a framework for future studies. By comparing Random Forest and LSTM models, we also highlight their respective strengths and limitations, offering practical insights for investors and analysts.