Data Modeling
Mathematical and Computational Data Modeling
1
Citations
6k
Views
37
Articles
Volume 3 Number 1 2022
RESEARCH ARTICLE (Open Access)
Financial News Sentiment and Stock Price Movement: An LSTM-Based Machine Learning Approach
Iffat Jahan 1*
Data Modeling 3 (1) 1-8 https://doi.org/10.25163/data.3110810
Submitted: 28 September 2022 Revised: 14 December 2022 Accepted: 19 December 2022 Published: 20 December 2022
Abstract
Whether the emotional tone of financial news genuinely anticipates price movement, or only appears to once the outcome is already known, is a question that has resisted a tidy answer for years — and this study revisits it empirically rather than assuming either side. Background: unstructured signals such as financial headlines are widely believed to carry information that historical prices alone cannot capture, yet the evidence remains mixed across markets and modelling choices. Methods: using a labelled corpus of more than 200,000 financial news headlines and seven years of company-level closing-price data for Apple Inc. (AAPL), we built a two-stage pipeline — a Naive Bayes and Support Vector Machine sentiment classifier, followed by a Long Short-Term Memory (LSTM) network that forecasts next-day price movement from both sentiment and price history. A closing-price-only LSTM served as the comparison baseline. Results: the sentiment classifier reached approximately 75% accuracy, and the sentiment-augmented LSTM outperformed the price-only variant, particularly during recovery phases of the test window. Correlational analysis further showed sentiment and price moving in the same direction on most observed trading days. Conclusion: financial news sentiment appears to carry real, if still modest, predictive value beyond price history alone, and improving sentiment-classification accuracy is likely the most direct route toward sharper forecasts. The findings, while limited to a single company and a comparatively small news corpus, are broadly consistent with prior work from other exchanges and modelling frameworks.
Keywords: financial news sentiment; stock price prediction; Long Short-Term Memory (LSTM); Naive Bayes; Support Vector Machine; time-series forecasting
References
Akter, S., & Aziz, M. T. (2016). Sentiment analysis on Facebook group using lexicon-based approach. In 2016 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT) (pp. 1–4). IEEE. https://doi.org/10.1109/ICEEICT.2016.7873080
Arif, M. H., Li, J., Iqbal, M., & Liu, K. (2018). Sentiment analysis and spam detection in short informal text using learning classifier systems. Soft Computing, 22(21), 7281–7291. https://doi.org/10.1007/s00500-017-2729-x
Batra, R., & Daudpota, S. M. (2018). Integrating StockTwits with sentiment analysis for better prediction of stock price movement. In 2018 International Conference on Computing, Mathematics and Engineering Technologies (ICoMET) (pp. 1–5). IEEE. https://doi.org/10.1109/ICOMET.2018.8346382
Biswas, S., Ghosh, A., Chakraborty, S., Roy, S., & Bose, R. (2020). Scope of sentiment analysis on news articles regarding stock market and GDP in struggling economic condition. International Journal of Emerging Trends in Engineering Research, 8(7), 3594–3609. https://doi.org/10.30534/ijeter/2020/117872020
Bonta, V., Kumaresh, N., & Janardhan, N. (2019). A comprehensive study on lexicon-based approaches for sentiment analysis. Asian Journal of Computer Science and Technology, 8(S2), 1–6.
Budiharto, W. (2021). Data science approach to stock prices forecasting in Indonesia during COVID-19 using Long Short-Term Memory (LSTM). Journal of Big Data, 8(1), Article 47. https://doi.org/10.1186/s40537-021-00430-0
Chaudhuri, A., Mukherjee, S., Chowdhury, S., & Sadhukhan, B. (2018). Fractality and stationarity analysis on stock market. In 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) (pp. 395–398). IEEE. https://doi.org/10.1109/ICACCCN.2018.8748504
Chauhan, P., Sharma, N., & Sikka, G. (2021). The emergence of social media data and sentiment analysis in election prediction. Journal of Ambient Intelligence and Humanized Computing, 12(2), 2601–2627. https://doi.org/10.1007/s12652-020-02423-y
Chou, C., Park, J., & Chou, E. (2021). Predicting stock closing price after COVID-19 based on sentiment analysis and LSTM. In 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) (Vol. 5, pp. 2752–2756). IEEE. https://doi.org/10.1109/IAEAC50856.2021.9390845
Derakhshan, A., & Beigy, H. (2019). Sentiment analysis on stock social media for stock price movement prediction. Engineering Applications of Artificial Intelligence, 85, 569–578. https://doi.org/10.1016/j.engappai.2019.07.002
Dutta, A., Pooja, G., Jain, N., Panda, R. R., & Nagwani, N. K. (2021). A hybrid deep learning approach for stock price prediction. In A. Joshi, M. Khosravy, & N. Gupta (Eds.), Machine learning for predictive analysis (pp. 1–10). Springer. https://doi.org/10.1007/978-981-15-7106-0
Eck, M., Germani, J., Sharma, N., Seitz, J., & Ramdasi, P. P. (2021). Prediction of stock market performance based on financial news articles and their classification. In N. Sharma, A. Chakrabarti, V. E. Balas, & J. Martinovic (Eds.), Data management, analytics and innovation (pp. 35–44). Springer.
Elena, P. (2021). Predicting the movement direction of OMXS30 stock index using XGBoost and sentiment analysis [Bachelor’s thesis, Blekinge Institute of Technology]. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-21119
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media.
Li, X., Wu, P., & Wang, W. (2020). Incorporating stock prices and news sentiments for stock market prediction: A case of Hong Kong. Information Processing & Management, 57(5), Article 102212. https://doi.org/10.1016/j.ipm.2020.102212
Li, X., Xie, H., Chen, L., Wang, J., & Deng, X. (2014). News impact on stock price return via sentiment analysis. Knowledge-Based Systems, 69, 14–23. https://doi.org/10.1016/j.knosys.2014.04.022
Mohan, S., Mullapudi, S., Sammeta, S., Vijayvergia, P., & Anastasiu, D. C. (2019). Stock price prediction using news sentiment analysis. In 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService) (pp. 205–208). IEEE. https://doi.org/10.1109/BigDataService.2019.00035
Pavitha, N., Pungliya, V., Raut, A., Bhonsle, R., Purohit, A., Patel, A., & Shashidhar, R. (2022). Movie recommendation and sentiment analysis using machine learning. Global Transitions Proceedings, 3(1), 279–284. https://doi.org/10.1016/j.gltp.2022.03.012
Shynkevich, Y., McGinnity, T. M., Coleman, S., & Belatreche, A. (2015). Predicting stock price movements based on different categories of news articles. In 2015 IEEE Symposium Series on Computational Intelligence (pp. 703–710). IEEE. https://doi.org/10.1109/SSCI.2015.107
Su, J., Shirab, J. S., & Matwin, S. (2011). Large scale text classification using semisupervised multinomial Naive Bayes. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011).
Syeda, F. S. (2022). Sentiment analysis of financial news with supervised learning [Unpublished manuscript].
Recommended articles
Integrating Artificial Intelligence and Machine Learning into U.S. Financial Risk Management Systems
Optimizing Resource Allocation and Operational Efficiency in Management Information Systems Using Predictive Machine Learning
Article metrics
View details
0
Downloads
0
Citations
76
Views
0
Save
Save
0
Citation
Citation
76
View
View
0
Share
Share