Stock price prediction plays a vital role in risk evaluation, investment decision-making, and financial planning. Traditional forecasting models primarily rely on technical indicators and historical price trends; however, they often fail to account for the emotional and behavioral dynamics influencing market movements. This research introduces a hybrid model that integrates investor sentiment—extracted from online platforms such as social media and financial news—with historical market data. By merging quantitative trends with psychological insights, the proposed approach enhances prediction accuracy and adaptability. The system utilizes natural language processing techniques and a deep learning framework to analyze textual content and generate sentiment scores. Empirical results using real-world datasets demonstrate that sentiment-augmented models outperform conventional approaches in forecasting short-term trends and detecting market volatility. The paper also explores the practical implications for real-time prediction systems and addresses related ethical considerations.