Creating a stock market forecasting model is challenging for any emerging market, including the Indian stock market. This is mostly due to a lack of study, much of which has concentrated on historical prices to predict future values. Furthermore, stock price fluctuations in emerging markets are often affected by investor sentiment, which is shaped by economic factors including significant movements in Western stock markets, variations in global commodity prices, escalations of conflict such as the Middle East crisis and the Ukraine war, and actions taken by central banks. Current research and development of stock price forecasting algorithms does not account for investor sentiment derived from numerous economic aspects that impact price movement. To overcome this challenge, we have recognized the significance and necessity of sentiment analysis tools for retail investors in India to facilitate investing decisions. We have created a hybrid forecasting model that amalgamates sentiment analysis data derived from economic indicators with historical stock or index prices inside a Deep Learning multivariate Long Short-Term Memory (LSTM) framework to predict future opening and closing prices. This model is based on a Natural Language Understanding application to identify the Sentiment of investors from the financial information. The multivariate LSTM deep learning model achieved greater accuracy, indicating that the sentiment analysis data on economic information has a significant impact on the stock price movement. The precision of stock or index price forecasts using LSTM deep learning models is improved by using a sentiment analysis score derived from economic data through Natural Language Understanding (NLU). This research aims to elucidate retail investors’ perceptions of the influence of economic news sentiment on the Indian stock market and to determine the necessity for sentiment analysis technologies to support investing decisions. Future research may be undertaken in alternative markets to ascertain the degree to which investor or consumer opinion toward certain events influences price volatility, as shown by our findings. This technique may also be used to consumer-driven product forecasting models, in addition to financial instruments.