Abstract
Financial intelligence has become a research hotspot in recent years with the development of behavioral finance which introduces the social emotion and behavior factors in the decision-making. The data mining technology is widely used in the research on financial intelligence. This paper collected the investors’ comments from Social Network Sites (SNS) by crawler technology and segmented each piece of comment into words by Chinese text processing technology to build a financial sentiment lexicon. Applying the sentiment lexicon, a sentiment computing model based on SO-PMI algorithm was designed to compute the sentiment indices of the investors. Finally, the paper made an empirical analysis through linear regression between the return of the stock and its investors’ sentiment index. The result proved that the sentiment indices based on the investors’ comments are better to measure the investors’ sentiment and can be used to predict the stock return.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hui, B., Li, P.: Does investor sentiment predict stock returns? The evidence from Chinese stock market. J. Syst. Sci. Complex. 27(1), 130–143 (2014)
Zhu, B., Zhao, S.: The PSM-black-litterman model based on the sentiment mining. Times Finan. 36(12), 224–226, 229 (2016)
Dickinson, B., Hu, W.: Sentiment Analysis of Investor Opinions on Twitter (2015). http://dx.doi.org/10.4236/sn.2015.43008. Published Online July 2015
Lee, C.M., Shleifer, A., Thaler, R.H.: Investor sentiment and the closed-end fund puzzle. J. Finan. 46(1), 75–109 (1991)
Zhu, H.: Research and Implementation based on SNS Emotional Information of Stock Price Change Trend. Fudan University, Shanghai (2015)
Huang, F., Feng, S., Wang, D.: Mining topic sentiment in microblogging based on multi-feature fusion. Chin. J. Comput. 40(4), 872–888 (2017)
Yi, H., Cai, Y., Dong, D.: The research on construction and effect of stock market investor sentiment index in China. Price Theory Pract. 28(10), 130–133 (2017)
Huang, J.: The construction of the investors’ sentiment index based on social media. Contemp. Acc. 2(18), 18–20 (2015)
Liu, J., Lu, Y.: Survey on topic-focused web crawler. Appl. Res. Comp. 24(10), 26–29 (2007)
Wang, M., Sun, J.: Stock market returns, volatility and the role of investor sentiment in China. Econ. Res. J. 50(10), 75–83 (2004)
Lan, Q.: Research of collecting financial data from internet. Comput. Eng. Des. 32(5), 1829–1832 (2011)
Yu, Q.H., Meng, W.: Cointegration analysis on relation of investor sentiment and the composite index of shanghai stock exchange. Forecasting 29(5), 53–57 (2010)
Jing, R., He, X.: The construction of the investor’s sentiment in China. Contemp. Econ. 31(24), 43–47 (2016)
Tetlock, P.C.: Giving content to investor sentiment: the role of media in the stock market. J. Finan. 62(3), 1139–1168 (2007)
Acknowledgments
This work was supported by International Cooperation and Exchange Program, Ministry of Science and Technology of China (No. 4-9/2018), and Major Project of Philosophy and Social Science Research, Ministry of Education of China (No. 19JZD010). Juan Cheng, Jiaolong Fu, Yan Kang are the joint first authors, and Weihui Dai is the corresponding author of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, J., Fu, J., Kang, Y., Zhu, H., Dai, W. (2019). Sentiment Analysis of Social Networks’ Comments to Predict Stock Return. In: Milošević, D., Tang, Y., Zu, Q. (eds) Human Centered Computing. HCC 2019. Lecture Notes in Computer Science(), vol 11956. Springer, Cham. https://doi.org/10.1007/978-3-030-37429-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-37429-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37428-0
Online ISBN: 978-3-030-37429-7
eBook Packages: Computer ScienceComputer Science (R0)