Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 5 | Year 2026 | Article Id. IJECE-V13I5P119 | DOI : https://doi.org/10.14445/23488549/IJECE-V13I5P119

Multimodal Stock Price Prediction Using a Hybrid GRU–Multi-Head Attention Model with Ensemble Sentiment and Technical Indicators

Ajaykumar K. Kakde, Manisha P. Dale

Received Revised Accepted Published
14 Feb 2026 15 Mar 2026 18 Apr 2026 27 May 2026

Citation :

Ajaykumar K. Kakde, Manisha P. Dale, "Multimodal Stock Price Prediction Using a Hybrid GRU–Multi-Head Attention Model with Ensemble Sentiment and Technical Indicators," International Journal of Electronics and Communication Engineering, vol. 13, no. 5, pp. 224-237, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I5P119

Abstract

This proposed methodology introduces a hybrid model integrating sentiment scores with historical data and technical indicators. Ensemble sentiment scores were calculated using three sentiment methods: Financial Bidirectional Encoder Representations from Transformers (FinBERT), Robustly Optimized BERT Pretraining Approach (RoBERTa), and Distilled Robustly Optimized BERT Pretraining Approach (DistilRoBERTa). Sentiments were extracted from the Global Database of Events, Language and Tone (GDELT) Project, Google RSS feeds, and news articles from The Economic Times, alongside historical stock data from Yahoo Finance of selected NIFTY 50 companies spanning January 3, 2022, to November 15, 2025. A Gated Recurrent Unit-Multi-Head Attention (GRU-MHA) model was utilized to identify sequential dependencies and predict the next-day opening prices for Infosys, Tata Motors, Sun Pharma, and Tata Steel within the NIFTY 50 index. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Coefficient of Determination (R²), and Mean Absolute Percentage Error (MAPE). The ensemble sentiment-driven GRU-MHA model had low errors, with MAE = 0.1631 and RMSE = 0.2337 for Infosys and MAE = 0.7607 for Tata Steel. Most stocks had an MAPE of less than 1%, with Sun Pharma at 0.49% and Tata Steel at 0.52%. R² values above 0.92 across sectors and as high as 0.9893 showed high explanatory power, outperforming standalone sentiment models.

Keywords

Gated Recurrent Unit (Gru), Multi-Head Attention (MHA), Stock Market (SM), Stock Price (SP), Sentiment Analysis (SA), Ensemble Sentiment Analysis (ESA), Technical Analysis (TA).

References

  1. Jingyi Shen, and M. Omair Shafiq, “Short-term Stock Market Price Trend Prediction using a Comprehensive Deep Learning System,” Journal of Big Data, vol. 7, pp. 1-33, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  2. Pooja Mehta​, Sharnil Pandya​, and Ketan Kotecha, “Harvesting Social Media Sentiment Analysis to Enhance Stock Market Prediction using Deep Learning,” PeerJ Computer Science, vol. 7, pp. 1-21, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  3. Shraddha R. Khonde et al., “Sentiment Analysis and Stock Data Prediction Using Financial News Headlines Approach,” Artificial Intelligence Review, vol. 38, no. 3, pp. 999-1008, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  4. Jilin Zhang, Lishi Ye, and Yongzeng Lai, “Stock Price Prediction Using CNN-BiLSTM-Attention Model,” Mathematics, vol. 11, no. 9, pp. 1-18, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  5. Ching-Ru Ko, and Hsien-Tsung Chang, “LSTM-based Sentiment Analysis for Stock Price Forecast,” PeerJ Computer Science, vol. 7, pp. 1-23, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  6. Hum Nath Bhandari et al., “Predicting Stock Market Index using LSTM,” Machine Learning with Applications, vol. 9, pp. 1-15, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  7. Armin Lawi, Hendra Mesra, and Supri Amir, “Implementation of Long Short-Term Memory and Gated Recurrent Units on Grouped Time-series Data to Predict Stock Prices Accurately,” Journal of Big Data, vol. 9, 1-19, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  8. Paraskevas Koukaras, Christina Nousi, and Christos Tjortjis, “Stock Market Prediction Using Microblogging Sentiment Analysis and Machine Learning,” Telecom, vol. 3, no. 2, pp. 358-378, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  9. Burak Gülmez, “Stock Price Prediction with Optimized Deep LSTM Network with Artificial Rabbits Optimization Algorithm,” Expert Systems with Applications, vol. 227, pp. 1-16, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  10. Rui Ren, Desheng Dash Wu, and Tianxiang Li, “Forecasting Stock Market Movement Direction Using Sentiment Analysis and Support Vector Machine,” IEEE Systems Journal, vol. 13, no. 1, pp. 760-770, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
  11. Qing Ge, “Enhancing Stock Market Forecasting: A Hybrid Model for Accurate Prediction of S&P 500 and CSI 300 Future Prices,” Expert Systems with Applications, vol. 260, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  12. Yanli Zhao, and Guang Yang, “Deep Learning-based Integrated Framework for Stock Price Movement Prediction,” Applied Soft Computing, vol. 133, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  13. Burak Gülmez, “GA-Attention-Fuzzy-Stock-Net: An Optimized Neuro-fuzzy System for Stock Market Price Prediction with Genetic Algorithm and Attention Mechanism,” Heliyon, vol. 11, no. 3, pp. 1-23, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  14. Zhinzhong Liu et al., “An Approach to Stock Price Prediction based on Improved EEMD and Attention-enhanced BiLSTM,” Expert Systems with Applications, vol. 284, pp. 1-23, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  15. Pengju Zhang, Richard D.F. Harris, and Jin Zheng, “GNN-based Social Media Sentiment Analysis for Stock Market Forecasting and Trading,” Expert Systems with Applications, vol. 291, pp. 1-20, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  16. Chih-Fong Tsai et al., “Predicting High Increases in Stock Prices using Text Mining and Data Resampling Techniques,” Applied Soft Computing, vol. 176, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  17. Tzu-Chia Chen et al., “Deep Learning-based Feature Fusion and Forecasting Approach for Stock Market Prediction,” Applied Soft Computing, vol. 182, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  18. Ralph C. Verhoeks, Willem F.C. Verschoor, and Remco C.J. Zwinkels, “Investor Attention and Stock Markets Dynamics: Evidence from the COVID-19 Pandemic,” Journal of Behavioral and Experimental Finance, vol. 48, pp. 1-18, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  19. Ashy Sebastian, and Dr. Veerta Tantia, “Multi-variate LSTM with Attention Mechanism for the Indian Stock Market,” International Journal of Information Management Data Insights, vol. 5, no. 2, pp. 1-15, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  20. Surabhi Adhikari et al., “Explainable Hybrid Word Representations for Sentiment Analysis of Financial News,” Neural Networks, vol. 164, pp. 115-123, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  21. Wen-Jie Liu, Ye-Bo Ge, and Yu-Chen Gu, “News-driven Stock Market Index Prediction based on Trellis Network and Sentiment Attention Mechanism,” Expert Systems with Applications, vol. 250, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  22. Guangyu Mu et al., “A Stock Price Prediction Model based on Investor Sentiment and Optimized Deep Learning,” IEEE Access, vol. 11, pp. 51353-51367, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  23. Shilpa Gite et al., “Explainable Stock Prices Prediction from Financial News Articles using Sentiment Analysis,” PeerJ Computer Science, vol. 7, pp. 1-21, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  24. Erman Arif1, Suherman Suherman, and Aris Puji Widodo, “Integration of Technical Analysis and Machine Learning to Improve Stock Price Prediction Accuracy,” Mathematical Modelling of Engineering Problems, vol. 11, no. 11, pp. 2929-2943, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  25. Marah-Lisanne Thormann et al., “Stock Price Predictions with LSTM Neural Networks and Twitter Sentiment,” Statistics, Optimization & Information Computing, vol. 9, no. 2, pp. 268-287, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  26. Pranjali Kasture, and Kamini Shirsath, “Enhancing Stock Market Prediction: A Hybrid RNN-LSTM Framework with Sentiment Analysis,” Indian Journal of Science and Technology, vol. 17, no. 18, pp. 1880-1888, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  27. Zuleaizal Sidek et al., “Associating Deep Learning and the News Headlines Sentiment for Bursa Stock Price Prediction,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 31, no. 2, pp. 1041-1049, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  28. Deeksha Chandola et al., “Forecasting Directional Movement of Stock Prices using Deep Learning Published,” Annals of Data Science, vol. 10, pp. 1361-1378, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  29. Filipe Correia, Ana Maria Madureira, and Jorge Bernardino, “Deep Neural Networks Applied to Stock Market Sentiment Analysis,” Sensors, vol. 22, no. 12, pp. 1-25, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
  30. Ali Raza et al., “Advanced Deep Learning-Based Predictive Modelling for Analyzing Trends and Performance Metrics in Stock Market,” Journal of Accounting and Finance in Emerging Economies, vol. 9, no. 3, pp. 277-294, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  31. Quyen Pham et al., “Revisiting the Role of Investor Sentiment in the Stock Market,” International Review of Economics and Finance, vol. 100, pp. 1-16, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  32. Dost Muhammad et al., “An Explainable Deep Learning Approach for Stock Market Trend Prediction,” Heliyon, vol. 10, no. 21, pp. 1-15, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  33. Ashkan Safari, and Mohammad Ali Badamchizadeh, “DeepInvesting: Stock Market Predictions with a Sequence-oriented BiLSTM Stacked Model – A Dataset Case Study of AMZN,” Intelligent Systems with Applications, vol. 24, pp. 1-13, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  34. M. Nabipour et al., “Deep Learning for Stock Market Prediction,” Entropy, vol. 22, no. 8, pp. 1-23, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  35. Can Yang, Junjie Zhai, and Guihua Tao, “Deep Learning for Price Movement Prediction Using Convolutional Neural Network and Long Short-Term Memory,” Mathematical Problems in Engineering, vol. 2020, pp. 1-13, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  36. Nan Jing, Zhao Wu, and Hefei Wang, “A Hybrid Model Integrating Deep Learning with Investor Sentiment Analysis for Stock Price Prediction,” Expert Systems with Applications, vol. 178, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  37. Adnan Gumus, and C. Okan Sakar, “Stock Market Prediction by Combining Stock Price Information and Sentiment Analysis,” International Journal of Advanced Engineering and Pure Science, vol. 33, no. 1, pp. 18-27, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  38. Rajesh Kumar Ghosh et al., “Deep Learning-Based Hybrid Model with Multi-Head Attention for Multi-Horizon Stock Price Prediction,” Journal of Risk and Financial Management, vol. 18, no. 10, pp. 1-27, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  39. Tzu-Chia Chen, “Deep Learning-based Feature Fusion and Forecasting Approach for Stock Market Prediction,” Applied Soft Computing, vol. 182, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  40. Farzaneh Ghorbani, Denis Helic, and Daniel Dan, “Utilizing Fuzzy Reinforcement Learning for Prediction in Volatile Stock Markets,” Array, vol. 30, pp. 1-11, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
  41. Le Yu, Yaoquan Chen, and Yanting Zheng, “A Multi-Market Data-Driven Stock Price Prediction System: Model Optimization and Empirical Study,” IEEE Access, vol. 13, pp. 65884-65899, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  42. The GDELT Projects. [Online]. Available: https://www.gdeltproject.org/
  43. Google News RSS Feed, RSS.app. [Online]. Available: https://rss.app/rss-feed/google-news-rss-feed
  44. The Economic Times. [Online]. Available: https://economictimes.indiatimes.com/
  45. FinBERT, Hugging Face. [Online]. Available : https://huggingface.co/ProsusAI/finbert
  46. Twitter-RoBERTa-base for Sentiment Analysis, Hugging Face. [Online]. Available: https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment
  47. DistilRoberta-Financial-Sentiment, Hugging Face. [Online]. Available: https://huggingface.co/mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis