A Hybrid Framework for Stock-Market Prediction Using COVID-19 Tweets through Nature-Inspired Algorithms and Machine Learning

Muhammad Nauman Khan; Saman Iftikhar; Daniah Al-Madani; Umer Zaheer; Danish khan; Kiran Fatima; Ammar Saeed

doi:10.31081/dmame8220251600

Authors

Muhammad Nauman Khan Faculty of Business Studies, Arab Open University, Saudi Arabia
Saman Iftikhar Faculty of Computer Studies, Arab Open University, Saudi Arabia
Daniah Al-Madani Faculty of Computer Studies, Arab Open University, Saudi Arabia
Umer Zaheer Faculty of Business Studies, Arab Open University, Saudi Arabia
Danish khan COMSATS University Islamabad, Wah Campus, Pakistan.
Kiran Fatima Technical and Further Education, TAFE, New South Wales, Australia.
Ammar Saeed COMSATS University Islamabad, Wah Campus, Pakistan

DOI:

https://doi.org/10.31081/dmame8220251600

Keywords:

Evolutionary Computing, Stock Exchange Prediction, Covid-19, Evolutionary Algorithm, Particle Swarm Optimization, and Genetic Algorithm.

Abstract

The COVID-19 outbreak generated severe disturbances across international financial systems, intensifying volatility within equity markets. Stock market behaviour during this period exhibited pronounced instability, shaped by broader economic conditions as well as collective investor sentiment. This study investigates the effect of COVID-19 related discourse on Twitter on market behaviour and proposes a hybrid modelling framework aimed at enhancing the accuracy of stock price movement forecasts. The proposed framework incorporates nature inspired optimisation techniques, including genetic algorithms, Harris hawk’s optimisation, particle swarm optimisation, and differential evolution. The methodological focus lies in embedding social media sentiment into predictive models to uncover latent relationships that are typically overlooked by conventional statistical approaches. Empirical results demonstrate that all hybrid configurations consistently surpassed traditional forecasting methods. Among them, the support vector regression model optimised using Harris hawk’s optimisation achieved superior performance, recording an MSE of 0.00014, an RMSE of 0.00214, and an MAE of 0.00170. These findings underscore the substantial influence of public sentiment on financial market dynamics during periods of global disruption and highlight the effectiveness of hybrid predictive approaches. Such models offer valuable support for stock market forecasting and provide actionable insights for decision makers operating under heightened economic uncertainty.

Downloads

Download data is not yet available.

References

[1] Abdullah, M., Sulong, Z., & Chowdhury, M. A. F. (2023). Explainable Deep Learning Model for Stock Price Forecasting Using Textual Analysis. https://doi.org/10.1016/j.eswa.2024.123740

[2] Abedin, M. Z., Moon, M. H., Hassan, M. K., & Hajek, P. (2025). Deep learning-based exchange rate prediction during the COVID-19 pandemic. Annals of Operations Research, 345(2), 1335-1386. https://doi.org/10.1007/s10479-021-04420-6

[3] Al-Hashedi, A., Al-Fuhaidi, B., Mohsen, A. M., Ali, Y., Al-Kaf, H. A. G., Al-Sorori, W., & Maqtary, N. (2022). Ensemble classifiers for arabic sentiment analysis of social network (twitter data) towards covid-19-related conspiracy theories. Applied Computational Intelligence and Soft Computing, 2022. https://doi.org/10.1155/2022/6614730

[4] Albahli, S. (2022). Twitter sentiment analysis: An Arabic text mining approach based on COVID-19. Frontiers in Public Health, 10, 966779. https://doi.org/10.3389/fpubh.2022.966779

[5] Alotaibi, M. N., & Alharbi, Z. H. (2022). Sentiment analysis to explore user perception of teleworking in Saudi Arabia. International Journal of Advanced Computer Science and Applications, 13(5). http://doi.org/10.14569/IJACSA.2022.0130565

[6] Alqarni, A., & Rahman, A. (2023). Arabic tweets-based sentiment analysis to investigate the impact of COVID-19 in KSA: a deep learning approach. Big Data and Cognitive Computing, 7(1), 16. https://doi.org/10.3390/bdcc7010016

[7] Aslam, N., Khan, I.U., AlKhales, T., AlMakki, R., AlNajim, S., Almarshad, S. and Saad, R., . (2022). Sentiment analysis on Education transformation during Covid-19 using Arabic tweets in KSA. International Journal of Emerging Multidisciplinaries: Computer Science & Artificial Intelligence, 2(1), 35-45. https://ojs.ijemd.com/index.php/ComputerScienceAI/article/view/137

[8] Bacanin, N., Zivkovic, M., Jovanovic, L., Ivanovic, M., & Rashid, T. A. (2022). Training a multilayer perception for modeling stock price index predictions using modified whale optimization algorithm. In Computational Vision and Bio-Inspired Computing. Springer. https://doi.org/10.1007/978-981-16-9573-5_31

[9] Balaha, H. M., Antar, E. R., Saafan, M. M., & El-Gendy, E. M. (2023). A comprehensive framework towards segmenting and classifying breast cancer patients using deep learning and Aquila optimizer. Journal of Ambient Intelligence and Humanized Computing, 14(6), 7897-7917. https://doi.org/10.1007/s12652-023-04600-1

[10] Balaha, H. M., El-Gendy, E. M., & Saafan, M. M. (2022). A complete framework for accurate recognition and prognosis of COVID-19 patients based on deep transfer learning and feature classification approach. Artificial Intelligence Review, 55(6), 5063-5108. https://doi.org/10.1007/s10462-021-10127-8

[11] Balaha, H. M., & Saafan, M. M. (2021). Automatic exam correction framework (AECF) for the MCQs, essays, and equations matching. Ieee Access, 9, 32368-32389. https://doi.org/10.1109/ACCESS.2021.3060940

[12] Boru İpek, A. (2023). Stock price prediction using improved extreme learning machine methods during the Covid-19 pandemic and selection of appropriate prediction method. Kybernetes, 52(10), 4081-4109. https://doi.org/10.1108/K-12-2021-1252

[13] Chaouachi, M., & Chaouachi, S. (2020). Current covid-19 impact on Saudi stock market: Evidence from an ARDL model. International Journal of Accounting Finance Auditing Management and Economics, 1(1), 1-13. https://revue.ijafame.com/index.php/home/article/view/8

[14] Elsegai, H., Al-Mutawaly, H. S., & Almongy, H. M. (2025). Predicting the Trends of the Egyptian Stock Market Using Machine Learning and Deep Learning Methods. Computational Journal of Mathematical and Statistical Sciences, 4(1), 186-221. https://journals.ekb.eg/article_396438_0.html

[15] Fahmy, H., El-Gendy, E. M., Mohamed, M. A., & Saafan, M. M. (2023). ECH3OA: an enhanced chimp-harris hawks optimization algorithm for copyright protection in color images using watermarking techniques. Knowledge-Based Systems, 269. https://doi.org/10.1016/j.knosys.2023.110494

[16] González-Núñez, E., Trejo, L. A., & Kampouridis, M. (2025). Expanding a machine learning class towards its application to the stock-market forecast. Applied Intelligence, 55(1). https://doi.org/10.1007/s10489-024-06018-4

[17] Gülmez, B. (2025). GA-Attention-Fuzzy-Stock-Net: An optimized neuro-fuzzy system for stock-market price prediction with genetic algorithm and attention mechanism. Heliyon, 11(3). https://doi.org/10.1016/j.heliyon.2025.e42393

[18] Jalil, Z., Abbasi, A., Javed, A. R., Khan, M. B., Hasanat, M. H. A., Malik, K. M., & Saudagar, A. K. J. (2022). Covid-19 related sentiment analysis using state-of-the-art machine learning and deep learning techniques. Frontiers in Public Health, 9. https://doi.org/10.3389/fpubh.2021.812735

[19] Jana, R. K., & Ghosh, I. (2025). A residual driven ensemble machine learning approach for forecasting natural gas prices: Analyses for pre-and during-COVID-19 phases. Annals of Operations Research, 345(2), 757-778. https://doi.org/10.1007/s10479-021-04492-4

[20] Kamali, A. H., Iranmanesh, S. H., & Goodarzian, F. (2024). Portfolio optimization in the stock-market under disruptions: Real case studies of COVID-19 pandemic and currency risk. Engineering Applications of Artificial Intelligence, 136. https://doi.org/10.1016/j.engappai.2024.108973

[21] Mahyoob, M., Algaraady, J., Alrahiali, M., & Alblwi, A. (2022). Sentiment analysis of public tweets towards the emergence of SARS-CoV-2 Omicron variant: A social media analytics framework. Engineering, Technology & Applied Science Research, 12(3), 8525-8531. https://doi.org/10.48084/etasr.4865

[22] Mati, S., Ismael, G. Y., Usman, A. G., Samour, A., Aliyu, N., Alsakarneh, R. A. I., & Abba, S. I. (2025). Gaussian random fuzzy and nature-inspired neural networks: a novel approach to Brent oil price prediction. Neural Computing and Applications, 1-19. https://doi.org/10.1007/s00521-025-11306-2

[23] Mizdrakovic, V., Kljajic, M., Zivkovic, M., Bacanin, N., Jovanovic, L., Deveci, M., & Pedrycz, W. (2024). Forecasting bitcoin: Decomposition aided long short-term memory based time series modelling and its explanation with shapley values. Knowledge-Based Systems. https://doi.org/10.1016/j.knosys.2024.112026

[24] Raghunathan, D., & Krishnamoorthi, M. (2025). Optimizing stock predictions with Bi-directional LSTM and levy flight fuzzy social spider optimization (LFFSSO): LSTM model. International Journal on Semantic Web and Information Systems, 21(1), 1-25. http://doi.org/10.4018/IJSWIS.367280

[25] Saafan, M. M., & El-Gendy, E. M. (2021). IWOSSA: An improved whale optimization salp swarm algorithm for solving optimization problems. Expert Systems with Applications, 176. https://doi.org/10.1016/j.eswa.2021.114901

[26] Vaiyapuri, T., Jagannathan, S. K., Ahmed, M. A., Ramya, K. C., Joshi, G. P., Lee, S., & Lee, G. (2023). Sustainable Artificial Intelligence-Based Twitter Sentiment Analysis on COVID-19 Pandemic. Sustainability, 15(8). https://doi.org/10.3390/su15086404

[27] Wang, Y., Wei, W., Liu, Z., Liu, J., Lv, Y., & Li, X. (2025). Interpretable machine learning framework for corporate financialization prediction: A SHAP-based analysis of high-dimensional data. Mathematics, 13(15), 2526. https://doi.org/10.3390/math13152526

[28] Wei, D., Wang, Z., & Qiu, M. (2025). Multiple objectives escaping bird search optimization and its application in stock-market prediction based on transformer model. Scientific Reports, 15. https://doi.org/10.1038/s41598-025-88883-8

[29] Yang, C., Abedin, M. Z., Zhang, H., Weng, F., & Hajek, P. (2025). An interpretable system for predicting the impact of COVID-19 government interventions on stock-market sectors. Annals of Operations Research, 347(2), 1031-1058. https://doi.org/10.1007/s10479-023-05311-8

[30] Zammarchi, G., Mola, F., & Conversano, C. (2023). Using sentiment analysis to evaluate the impact of the COVID-19 outbreak on Italy’s country reputation and stock-market performance. Statistical Methods & Applications. https://doi.org/10.1007/s10260-023-00690-5

[31] Zivkovic, M., Stoean, C., Petrovic, A., Bacanin, N., Strumberger, I., & Zivkovic, T. (2021). A novel method for covid-19 pandemic information fake news detection based on the arithmetic optimization algorithm. 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, IEEE. https://doi.org/10.1109/SYNASC54541.2021.00051