During the past few decades, time series analysis has become one popular method for solving stock
forecasting problem. However, depending only on stock index series makes the performance of the forecast not
good enough, because many external factors which may be involved are not taken into consideration. As a way to
deal with it, sentiment analysis on online textual data of stock market can generate a lot of valuable information as
a complement which can be named as external indicators. In this paper, a new method which combines the time
series of external indicators and the time series of stock index is provided. A special text processing algorithm
is proposed to obtain a weighted sentiment time series. In the experiment, we obtain financial micro-blogs from
some famous portal websites in China. After that, each micro-blog is segmented and preprocessed, and then the
sentiment value is calculated for each day. Finally, an NARX time series model combined with the weighted
sentiment series is created to forecast the future value of Shanghai Stock Exchange Composite Index (SSECI).
The experiment shows that the new model makes an improvement in terms of the accuracy.
WANG Yinglin (王英林)
. Stock Market Forecasting with Financial Micro-Blog Based on Sentiment and Time Series Analysis[J]. Journal of Shanghai Jiaotong University(Science), 2017
, 22(2)
: 173
-179
.
DOI: 10.1007/s12204-017-1818-4
[1] PEDRYCZ W, CHEN S M. Time series analysis, modelingand applications [M]. Berlin: Springer-Verlag,2013.
[2] WANG L, ZOU H F, SU J, et al. An ARIMA-ANNhybrid model for time series forecasting [J]. SystemsResearch and Behavioral Science, 2013, 30: 244-259.
[3] CORTEZ P, RIO M, ROCHA M, et al. Multi-scaleInternet traffic forecasting using neural networks andtime series methods [J]. Expert Systems, 2012, 29(2):143-155.
[4] KUMAR D A, MURUGAN S. Performance analysisof Indian stock market index using neural networktime series model [C]//Proceedings of the 2013 InternationalConference on Pattern Recognition, Informaticsand Mobile Engineering (PRIME). [s. l.]: IEEE,2013: 72-78.
[5] O’CONNOR N, MADDEN M G. A neural network approachto predicting stock exchange movements usingexternal factors [J]. Knowledge-Based Systems, 2006,19(5): 371-378.
[6] SCHUMAKER R P, ZHANG Y L, HUANG C N, etal. Evaluating sentiment in financial news articles [J].Decision Support Systems, 2012, 53(3): 458-464.
[7] LIANG X, CHEN R C, HE Y, et al. Associatingstock prices with web financial information time seriesbased on support vector regression [J]. Neurocomputing,2013, 115: 142-149.
[8] HAGENAU M, LIEBMANN M, NEUMANN D. Automatednews reading: Stock price prediction basedon financial news using context-capturing features [J].Decision Support Systems, 2013, 55: 685-697.
[9] RUIZ E J, HRISTIDIS V, CASTILLO C, et al. Correlatingfinancial time series with micro-blogging activity[C]// Proceedings of the fifth ACM International Conferenceon Web Search and Data Mining. New York,USA: ACM, 2012: 513-522.
[10] BOLLEN J, MAO H, ZENG X J. Twitter mood predictsthe stock market [J]. Journal of ComputationalScience, 2011, 2(1): 1-8.
[11] LI Q, WANG J, WANG F, et al. The role of socialsentiment in stock markets: A view from joint effects ofmultiple information sources [J]. Multimedia Tools andApplications, 2016. DOI: 10. 1007/s11042-016-3643-4(published online).
[12] ROMANOWSKI A, SKUZA M. Towards predictingstock price moves with aid of sentiment analysis ofTwitter social network data and big data processingenvironment [C]// Advances in Business ICT: NewIdeas from Ongoing Research, Studies in ComputationalIntelligence. [s.l.]: Springer International Publishing,2017: 105-123.
