Stock price prediction using sentimental analysis and deep learning for Indian market

This study explores stock market prediction through sentiment analysis, leveraging natural language processing (NLP) techniques to evaluate the emotional tone of financialnews, social media, and investor commentary. Sentiment scores are integrated with historical stock price data to enhance the accuracy of stock price movement forecasts. Thestudy employs a hybrid modeling approach that includes ARIMA for time-series forecasting, Decision Tree models for interpretable pattern recognition, and advanced deeplearning architectures such as Long Short-Term Memory (LSTM) and Transformer models to capture complex temporal dependencies and long-range contextual information.The experimental results demonstrate that sentiment-driven features, when combinedwith traditional financial indicators, significantly improve predictive performance. Thisresearch highlights the effectiveness of sentiment analysis integrated with both statisticaland deep learning models as a valuable decision-support tool for investors and financialanalysts, particularly under volatile market conditions.