Copyright © 2025 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{173307,
        author = {saranarayanan R and MR Anbuthiruvarangan k and sakthi harirajan R and logesvaran. Sk},
        title = {stock market analysis and prediction in sentiment analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {2959-2967},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173307},
        abstract = {Artificial Intelligence (AI) has rapidly evolved into a transformative field, fundamentally altering how data-driven predictions and decision-making processes are executed across various domains. Within financial analytics, Machine Learning (ML) and Deep Learning (DL) techniques have enabled advancements in stock market prediction, achieving accuracy levels in the range of 65–70%. However, inherent market volatility and the influence of numerous factors make predicting stock trends complex and less reliable when relying solely on single models. Decision fusion—an approach that combines predictions from multiple base models—has emerged as a promising solution, effectively mitigating the limitations of individual models by integrating their strengths. Yet, there is a scarcity of systematic studies examining the implementation of decision fusion specifically for stock market prediction. Our research addresses this gap, providing a comprehensive analysis of base learner properties, fusion techniques, and practical recommendations drawn from foundational studies, including our primary source material, to achieve improved prediction precision. The recent advancements and emerging directions within AI-driven financial forecasting. Notably, the integration of decision fusion with sentiment analysis has demonstrated potential in capturing market sentiments reflected in real-time data, such as news headlines and social media feeds. By combining sentiment insights with historical stock data and multi-source decision fusion, our approach offers a more holistic model for stock market prediction. Future directions include refining the model's capabilities to handle various data sources effectively, thus improving its adaptability and predictive power. Ultimately, this study aims to establish an advanced framework for stock market analysis, leveraging the latest in AI to provide more accurate and robust predictions that can support better-informed financial decision making in a constantly changing market landscape.},
        keywords = {Stock price prediction - Deep learning - Time series analysis - Long Short -Term Memory (LSTM) networks - Gated Recurrent Units (GRU)- Convolutional Neural Networks (CNN).},
        month = {May},
        }