Volume 25 • Issue 2 • PP: 176-182 • 2025
Sentimental Analysis to Predict Stock Market Using in Neutrosophic Time Series
View PDF Abstract
This study delves into the innovative use of sentiment analysis in conjunction with neutrosophic time series to forecast stock market trends in various contexts. By meticulously analyzing financial news and social media data, sentiment scores are derived and subsequently integrated into a neutrosophic time series model. This model is uniquely adept at managing uncertainty and indeterminacy, providing a robust framework for prediction. The findings indicate that this integrated approach significantly enhances predictive accuracy and reliability over traditional time series models. This research presents a novel methodology for tackling the intrinsic unpredictability of stock markets, offering a more reliable tool for investors and analysts across diverse financial environments. Additionally, by incorporating sentiment scores from a wide range of sources, the model captures a comprehensive view of market sentiment, reflecting the collective mood and opinions of investors. This comprehensive approach ensures that the predictions are not only accurate but also reflective of real-time market dynamics. Finally, this work highlights the possibility of merging sentiment analysis with sophisticated modeling approaches to change stock market prediction, as well as providing a promising avenue for future financial forecasting research.
Keywords
References
[1] Smarandache, F. (1999). A unifying field in Logics: Neutrosophic Logic. In Philosophy (pp. 1-141). American Research Press.
[2] Kandasamy, I., Vasantha, W. B., Obbineni, J. M., & Smarandache, F. (2020). Sentiment analysis of tweets using refined neutrosophic sets. Computers in Industry, 115, 103180.
[3] Abdel-Basset, M., Chang, V., Mohamed, M., & Smarandache, F. (2019). A refined approach for forecasting based on neutrosophic time series. Symmetry, 11(4), 457.
[4] Guan, H., Dai, Z., Guan, S., & Zhao, A. (2019). A neutrosophic forecasting model for time series based on first-order state and information entropy of high-order fluctuation. Entropy, 21(5), 455.
[5] Singh, P. (2020). A novel hybrid time series forecasting model based on neutrosophic-PSO approach. International Journal of Machine Learning and Cybernetics, 11(8), 1643-1658.
[6] Guan, H., He, J., Guan, S., & Zhao, A. (2019). Neutrosophic soft sets forecasting model for multi-attribute time series. IEEE Access, 7, 25575-25588.
[7] Singh, P. (2020). A novel hybrid time series forecasting model based on neutrosophic-PSO approach. International Journal of Machine Learning and Cybernetics, 11(8), 1643-1658.
[8] Edalatpanah, S. A., Hassani, F. S., Smarandache, F., Sorourkhah, A., Pamucar, D., & Cui, B. (2024). A hybrid time series forecasting method based on neutrosophic logic with applications in financial issues. Engineering applications of artificial intelligence, 129, 107531.
[9] Xu, Y., & Cohen, S. B. (2018, July). Stock movement prediction from tweets and historical prices. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1970-1979).
[10] Smarandache, F. (1999). A unifying field in Logics: Neutrosophic Logic. In Philosophy (pp. 1-141). American Research Press.
[11] Dias, B. C. D., Sadaei, H. J., e Silva, P. C. D. L., & Guimarães, F. G. (2021, May). Aggregation of Sentiment Analysis Index with Hesitant Fuzzy Sets for Financial Time Series Forecasting. In 2021 IEEE World AI IoT Congress (AIIoT) (pp. 0433-0439). IEEE.
Cite This Article
Choose your preferred format