Abstract
Sentiment analysis is a computational study of opinions, feelings, emotions, ratings and attitudes towards entities such as products, services, organizations, individuals, issues, events, subjects and their attributes. Our research is used to predict stock market movements, aims to improve the accuracy of polarity of comments, in order to accurately predict financial movements. This by creating a dictionary of emojis that contains the emoji as keys and its meanings as values. We used the dictionary at the preprocessing level to keep the meanings of emojis because they carry a lot of emotions that help us to clearly specify the polarity of the comments. We have also created a list of stopwords related to the financial field to properly clean our database. Time series and linking sequences of data is very important to properly predict stock market movements. We have therefore chosen to work with the Long short-term memory (LSTM) model. Next, we came up with two models: the first model to predict stock market movements using investor sentiment analysis of Amazon stock which gives us 93% accuracy. The second model is used to predict financial movements through historical Amazon prices. We extracted the database we used for the sentiment analysis from Twitter as the Twitter comments are up to date. As for the historical prices of Amazon stock we extracted from the most famous trading platform YahooFinance.
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
Similar content being viewed by others
References
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. J. 9, 1735–1780 (1997)
Kalyani, J., Bharathi, P., Jyothi, P.: Stock trend prediction using news sentiment analysis. Int. J. Comput. Sci. Inf. Technol. (IJCSIT) (2016)
Kordonis, J., Symeonidis, S., Arampatzis, A.: Stock price forecasting via sentiment analysis on Twitter. In: Proceedings of the 20th Pan-Hellenic Conference on Informatics, November 2016
Zhang, K., Li, L., Li, P., Teng, W.: Stock trend forecasting method based on sentiment analysis and system similarity model. In: Proceedings of 2011 6th International Forum on Strategic Technology, vol. 2, pp. 890–894 (2011)
Bhat, A., Kamath, S.: Automated stock price prediction and trading framework for Nifty intraday trading. In: 2013 Fourth International Conference on Computing, Communications and Networking Technologies, pp. 1–6 (2013)
Xu, Y., Keselj, V.: Stock prediction using deep learning and sentiment analysis. In: 2019 IEEE International Conference on Big Data (Big Data) (2019)
Liu, S., Zhang, X., Wang, Y., Feng, G.: Recurrent convolutional neural kernel model for stock price movement prediction. PLoS ONE 15, e0234206 (2020)
Gillham, D.: Trading the Stock Market - Why Most Traders Fail (2021). https://www.wealthwithin.com.au/learning-centre/share-trading-tips/trading-the-stock-market
Hugo, T.: What are the different types of financial risks (2020). https://study.com/academy/lesson/financial-risk-types-examples-management-methods.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mejbri, H., Mahfoudh, M., Forestier, G. (2022). Deep Learning-Based Sentiment Analysis for Predicting Financial Movements. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13369. Springer, Cham. https://doi.org/10.1007/978-3-031-10986-7_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-10986-7_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10985-0
Online ISBN: 978-3-031-10986-7
eBook Packages: Computer ScienceComputer Science (R0)