Stock market forecasting with financial micro-blog based on sentiment and time series analysis
- 110 Downloads
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.
Key wordstime series micro-blog sentiment analysis parsing neural network
CLC numberTP 181 TP 391
Unable to display preview. Download preview PDF.
- CORTEZ P, RIO M, ROCHA M, et al. Multi-scale Internet traffic forecasting using neural networks and time series methods [J]. Expert Systems, 2012, 29(2): 143–155.Google Scholar
- LI Q, WANG J, WANG F, et al. The role of social sentiment in stock markets: A view from joint effects of multiple information sources [J]. Multimedia Tools and Applications, 2016. DOI: 10. 1007/s11042-016-3643-4 (published online).Google Scholar
- ROMANOWSKI A, SKUZA M. Towards predicting stock price moves with aid of sentiment analysis of Twitter social network data and big data processing environment [C]//Advances in Business ICT: New Ideas from Ongoing Research, Studies in Computational Intelligence. [s.l.]: Springer International Publishing, 2017: 105–123.Google Scholar