Research Area:  Machine Learning
News from traditional media has been used to facilitate the prediction of stock movement for a long time. However, in recent times, online social networks (OSN) have played an increasing significant role as a platform for information sharing. News content posted on these OSN provides very useful insight about public moods. In this paper, we carefully select official accounts from Chinas largest online social networks — Sina Weibo and analyze the news content crawled from these accounts by extracting sentiment features and Latent Dirichlet allocation (LDA) features. We then input these features together with technical indicators into a novel hybrid model called RNN-boost to predict the stock volatility in the Chinese stock market. The Shanghai-Shenzhen 300 Stock Index (HS300) is the use case for this research. Experimental results show that our model outperforms other prevalent methods and can achieve a good prediction performance.
Author(s) Name:  WeilingChen,Chai KiatYeo,Chiew TongLau and Bu SungLee
Journal name:  Data & Knowledge Engineering
Publisher name:  ELSEVIER
Volume Information:  Volume 118, November 2018, Pages 14-24
Paper Link:   https://www.sciencedirect.com/science/article/abs/pii/S0169023X17305839