Abstract
It is well known that investors in stock market making financial decisions are often affected by certain events, like the coronavirus disease pandemic. However, it is very hard to perceive stock market crisis by making use of variety information. In this paper, we investigate whether it is possible to exploit arguments from investor sentiment expressed through financial news and posts, to forecast conditional stock market crisis. Thus, an argumentation enriched multi-agent sentiment classification method is proposed to make full use of variety tone and proliferation under certain events. In particular, the conditional stock market is investigated in our experiment to compare the predictive performance of the argumentation enriched multi-agent sentiment classification system with the existing multiple classifier system for the variance of CSI 300 Index. We find that the proposed argumentation enriched system outperforms the existing popular multiple classifier systems, while giving argumentative explanations through preliminary empirical evaluation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ye, X., et al.: Multi-view ensemble learning method for microblog sentiment classification. Expert Syst. Appl. 166, 113987 (2020)
Bellini, V., Guidolin, M., Pedio, M.: Can Big Data Help to Predict Conditional Stock Market Volatility? An Application to Brexit. Machine Learning, Optimization, and Data Science. Springer, Cham, 2020. https://doi.org/10.1007/978-3-030-64583-0_36
Costola, M., et al.: Machine learning sentiment analysis, Covid-19 news and stock market reactions. SAFE Working Paper Series (2020)
Conţiu, Ş, Groza, A.: Improving remote sensing crop classification by argumentation-based conflict resolution in ensemble learning. Expert Syst. Appl. 64, 269–286 (2016)
Hao, Z.-Y., Liu, T., Yang, C., Chen, X.: Context-aware layered learning for argumentation based multiagent collaborative recognition. In: Tan, Y., Shi, Y., Niu, B. (eds.) ICSI 2019. LNCS, vol. 11656, pp. 23–32. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-26354-6_3
Buzea, M.C., Trausan-Matu, S., Rebedea, T.: A three word-level approach used in machine learning for Romanian sentiment analysis. In: 2019 18th RoEduNet Conference: Networking in Education and Research (RoEduNet) IEEE (2019)
Hosamani, V., Vimala, H.S.: Data science: prediction and analysis of data using multiple classifier system. Int. J. Comput. Eng. Res. Trends (2019)
Huang, F., et al.: Attention-emotion-enhanced convolutional LSTM for sentiment analysis. IEEE Trans. Neural Netw. Learn. Syst. 99, 1–14 (2021)
Yang, K., Liao, C., Zhang, W.: A sentiment classification model based on multiple multi-classifier systems. In: Sun, X., Pan, Z., Bertino, E. (eds.) ICAIS 2019. LNCS, vol. 11633, pp. 287–298. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-24265-7_25
Araque, O., et al.: Enhancing deep learning sentiment analysis with ensemble techniques in social applications. Expert Syst. Appl. 77.C, 236–246 (2017)
Catal, C., Nangir, M.: A sentiment classification model based on multiple classifiers. Appl. Soft Comput. 50, 135–141 (2017)
Ghosh, M., Sanyal, G.: An ensemble approach to stabilize the features for multi-domain sentiment analysis using supervised machine learning. J. Big Data 5(1), 1–25 (2018). https://doi.org/10.1186/s40537-018-0152-5
Li, Y., et al.: Cooperative hybrid semi-supervised learning for text sentiment classification. Symmetry 11.2 (2019)
Zeng, Z., et al.: Context-based and explainable decision making with argumentation. In: Proceedings of the 17th International Conference on Autonomous Agents and Multi Agent Systems. International Foundation for Autonomous Agents and Multi-agent Systems (2018)
Gaggl, S.A., et al.: Design and results of the second international competition on computational models of argumentation. Artif. Intell. 279, 103193 (2019)
Sirrianni, J.W., Liu, X., Adams, D.: Predicting stance polarity and intensity in cyber argumentation with deep bidirectional transformers. IEEE Trans. Comput. Soc. Syst. 99, 1–13 (2021)
Fan, X., et al.: A first step towards explained activity recognition with computational abstract argumentation. In: 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI). IEEE (2016)
Ganzer-Ripoll, J., Criado, N., Lopez-Sanchez, M., Parsons, S., Rodriguez-Aguilar, J.A.: Combining social choice theory and argumentation: enabling collective decision making. Group Decis. Negot. 28(1), 127–173 (2018). https://doi.org/10.1007/s10726-018-9594-6
Hao, Z.-Y., Yang, C., Liu, L., Kustudic, M., Niu, B.: Exploiting skew-adaptive delimitation mechanism for learning expressive classification rules. Appl. Intell. 50(3), 746–758 (2019). https://doi.org/10.1007/s10489-019-01533-1
Acknowledgements
This work is supported by Guangdong Basic and Applied Basic Research Foundation (Project No. 2019A1515011392), and the basic research project of Shenzhen Institute of Information Technology (Project No. SZIIT2020SK013).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Hao, Zy., Sun, Pg. (2021). Can Argumentation Help to Forecast Conditional Stock Market Crisis with Multi-agent Sentiment Classification?. In: Tan, Y., Shi, Y. (eds) Advances in Swarm Intelligence. ICSI 2021. Lecture Notes in Computer Science(), vol 12690. Springer, Cham. https://doi.org/10.1007/978-3-030-78811-7_47
Download citation
DOI: https://doi.org/10.1007/978-3-030-78811-7_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78810-0
Online ISBN: 978-3-030-78811-7
eBook Packages: Computer ScienceComputer Science (R0)