Integrating Sentiment Analysis and Machine Learning for Robust Stock Price Prediction: A Comprehensive Study Exploring the Synergy of Sentiment Data and Historical Stock Prices for Accurate and Reliable Market Predictions

No Thumbnail Available
Authors
Wilson, Anup
Issue Date
2024
Degree
MSc in Data Analytics
Publisher
Dublin Business School
Rights
Abstract
The incorporation of sentiment analysis from Twitter data into stock price prediction models for well-known electric vehicle (EV) manufacturers, such as Tesla, Ford, Nio, and Xpeng, is investigated in this study. Sentiment scores are collected from tweets using natural language processing algorithms, and they are classified as positive, neutral, or negative. Subsequently, these sentiment scores are combined with historical stock price data to train various machine learning models, such as neural network, support vector machine (SVM), decision tree, random forest, MLP Regressor and linear regression models. The accuracy of each model is evaluated using metrics like mean squared error (MSE), mean absolute error (MAE), and R-squared value. The findings demonstrate how sentiment research may improve stock price predictions, with random forest models continuously beating other models. This indicates the ability to capture hidden nonlinear relationships between sentiment and stock price. The study highlights the growing significance of sentiment analysis in financial analysis and investment decision-making, not only in the electric vehicle industry but also providing investors with important market conditions information. The results add to the expanding amount of literature on sentiment analysis applications in finance, especially in the fast-paced electric vehicle (EV) sector. These applications may enhance overall stock market efficiency and provide guidance for strategic investment choices.