REFINING THE INFLUENCE OF SENTIMENT INTENSITY IN MARKET NEWS ON AI/ML STOCK PRICE PREDICTION MODELS.

Abstract

Integrating sentiment analysis from market news into artificial intelligence and machine learning (AI/ML) stock price prediction models has gained significant attention due to its potential to enhance forecasting accuracy. This study delves into the refinement of incorporating sentiment intensity from market news into AI/ML stock price prediction models. While existing research has explored the impact of sentiment analysis, there remains a need to understand how the intensity of sentiment expressed in news articles affects the predictive power of such models.

This research proposes a comprehensive approach to address this gap by developing a novel framework that quantifies sentiment intensity in market news and evaluates its impact on AI/ML stock price prediction accuracy. The framework harnesses advanced natural language processing techniques to extract and quantify sentiment intensity, capturing nuanced variations in sentiment expression. A diverse dataset of historical market news and stock price data is utilized for training and evaluation.

Through extensive experimentation, our findings reveal that refining AI/ML stock price prediction models with sentiment intensity significantly enhances their predictive capabilities. The proposed framework demonstrates that incorporating sentiment intensity provides a deeper understanding of market dynamics and improves the models' ability to capture price trends and fluctuations accurately. The study also examines the optimal integration of sentiment intensity alongside other relevant predictors.

Key Words:  Sentiment Intensity, Artificial intelligence, Machine Learning, Stock Pricing, Natural Language Processing, Algorithmic Trading System.