Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190758,
        author = {INDRAJA S and NIDHI K S and SURAJ S G and VISHWAS D G and Sayyed Johar},
        title = {Hybrid Deep Learning Framework for Stock Market Price Prediction Using News Sentiment and Time-Series Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {4985-4992},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190758},
        abstract = {Stock market price prediction is a challenging problem due to the highly dynamic nature of financial markets, which are influenced by both historical price movements and external factors such as public sentiment and real-world events. Traditional time-series forecasting models rely primarily on numerical data and often fail to capture the impact of news-driven market behavior. To address this limitation, this paper proposes a hybrid stock market prediction framework that integrates deep learning–based time-series modeling with news sentiment analysis. The proposed system employs a Long Short-Term Memory (LSTM) network trained on historical stock prices and derived technical indicators to model temporal dependencies in market trends. In parallel, financial news articles are processed using Natural Language Processing (NLP) techniques to extract sentiment scores that reflect market optimism or pessimism. These sentiment features are fused with numerical stock data to generate refined price predictions.
A web-based dashboard is developed to visualize live stock prices, candlestick charts, sentiment trends, and predicted price movements in real time, enabling intuitive analysis for investors and traders. Experimental evaluation demonstrates that the hybrid LSTM-sentiment model achieves improved prediction accuracy compared to conventional time-series forecasting approaches. The results highlight the effectiveness of combining quantitative market data with qualitative news sentiment, providing a robust decision-support tool for intelligent stock market analysis.},
        keywords = {Stock Market Prediction; News Sentiment Analysis; Deep Learning; Long Short-Term Memory (LSTM); Natural Language Processing; Financial Time-Series Forecasting; Technical Indicators; Decision Support System},
        month = {January},
        }