Which sentiment index is more informative to forecast stock market volatility? Evidence from China

Chao Liang, Linchun Tang, Yan Li and Yu Wei

International Review of Financial Analysis, 2020, vol. 71, issue C

Abstract: In this paper, we investigate the predictive ability of three sentiment indices constructed by social media, newspaper, and Internet media news to forecast the realized volatility (RV) of SSEC from in- and out-of-sample perspectives. Our research is based on the heterogeneous autoregressive (HAR) framework. There are several notable findings. First, the in-sample estimation results suggest that the daily social media and Internet media news sentiment indices have significant impact for stock market volatility, while the sentiment index built by traditional newspaper have no impact. Second, the one-day-ahead out-of-sample forecasting results indicate that the two sentiment indices constructed by social media and Internet media news can considerably improve forecast accuracy. In addition, the model incorporating the positive and negative social media sentiment indices exhibits more superior forecasting performance. Third, we find only the sentiment index built by Internet media news can improve the mid- and long-run volatility predictive accuracy. Fourth, the empirical results based on alternative prediction periods and alternative volatility estimator confirm our conclusions are robust. Finally, we examine the predictability of the monthly sentiment indices and find that the two sentiment indices of social media and Internet media news contain more informative to forecast the monthly RV of SSEC, CSI800, and SZCI, however invalid for CSI300.

Keywords: Chinese stock market; Sentiment index; Realized volatility; Forecasting (search for similar items in EconPapers)
JEL-codes: C22 C53 C58 G11 G12 G17 Q43 Q47 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (67)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1057521920301964
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finana:v:71:y:2020:i:c:s1057521920301964

DOI: 10.1016/j.irfa.2020.101552

Access Statistics for this article

International Review of Financial Analysis is currently edited by B.M. Lucey

More articles in International Review of Financial Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().