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{176739,
        author = {Darshan M S and Umme Kulsum and Gaurav H and Srivatsa K S and Manjunath K V},
        title = {Predicting Stock Market Trends: A Sentiment Aware Deep Learning Approach with LSTM and FinBERT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7982-7988},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176739},
        abstract = {Predicting the stock market has always been a difficult task that is impacted by a number of social, political, and economic variables. Using a complex neural network architecture, this study offers a novel deep learning method for comprehending and evaluating stock market sentiment and price prediction. The suggested model processes and assesses unstructured financial data by fusing traditional attention mechanism with Long Short-Term Memory (LSTM) networks. Dense layers with dropout regularization to avoid overfitting come next. By showcasing the efficacy of attention-based deep learning in sentiment-driven price prediction, this study advances financial market analytics. The model is a promising tool for financial analysts and algorithmic trading systems due to its high accuracy and interpretability, which could increase trading efficiency and market prediction accuracy. With an emphasis on sentiment-driven stock price prediction, this study investigates the use of cutting-edge machine learning techniques in financial market analytics thorough examination of past market trends and financial news. . The model derives valuable insights by utilizing natural language processing (NLP) methods like sentiment classification, contextual embedding, and tokenization. reached a low standard deviation of 1.65% and a high cross-validation accuracy of 87%, indicating its resilience in predicting stock price trends based on sentiment-driven market dynamics.},
        keywords = {Stock Price, Prediction, Machine Learning, LSTM, Mean Square Error, Attention mechanism, FinBert.},
        month = {May},
        }