Social media sentiment, model uncertainty, and volatility forecasting

doi:10.1016/j.econmod.2021.105556

CSpace

	Social media sentiment, model uncertainty, and volatility forecasting
	Lehrer, Steven 1,2; Xie, Tian 3; Zhang, Xinyu 4
	2021-09-01
发表期刊	ECONOMIC MODELLING
ISSN	0264-9993
卷号	102 页码:13
摘要	Many economic indicators including consumer confidence indices used to forecast volatility or macroeconomic outcomes, are published with a considerable time lag. To obtain a timelier measure of consumer sentiment many central bank and economic researchers are turning towards using state-of-the-art text sentiment analysis tools. We examine if there are benefits for forecasting volatility from (i) incorporating a sentiment measure derived using deep learning from Twitter messages at the 1-min level, and (ii) acknowledging specification uncertainty of the lag index in the heterogeneous autoregression (HAR) model. We present evidence from an out of sample forecasting exercise that suggests including social media sentiment can significantly improve the forecasting accuracy of a popular volatility index, particularly in short time horizons. Further, our results document large gains in predictive accuracy from a newly proposed estimator that allows for model uncertainty in the specification of the lag index when using a HAR estimator.
关键词	Model averaging Volatility forecasting Social media Big data Sentiment analysis
DOI	10.1016/j.econmod.2021.105556
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[71925007] ; Natural Science Foundation of China[72091212] ; Natural Science Foundation of China[11688101] ; Natural Science Foundation of China[71701175] ; Fundamental Research Funds for the Central Universities ; National Key R&D Program of China[2020AAA0105200] ; Beijing Academy of Artificial Intelligence ; Youth Innovation Promotion Association of Chinese Academy of Sciences ; SSHRC
WOS研究方向	Business & Economics
WOS类目	Economics
WOS记录号	WOS:000680417500005
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/59012
专题	中国科学院数学与系统科学研究院
通讯作者	Xie, Tian
作者单位	1.Queens Univ, Kingston, ON, Canada 2.NBER, Cambridge, MA 02138 USA 3.Shanghai Univ Finance & Econ, Coll Business, Shanghai, Peoples R China 4.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Lehrer, Steven,Xie, Tian,Zhang, Xinyu. Social media sentiment, model uncertainty, and volatility forecasting[J]. ECONOMIC MODELLING,2021,102:13.
APA	Lehrer, Steven,Xie, Tian,&Zhang, Xinyu.(2021).Social media sentiment, model uncertainty, and volatility forecasting.ECONOMIC MODELLING,102,13.
MLA	Lehrer, Steven,et al."Social media sentiment, model uncertainty, and volatility forecasting".ECONOMIC MODELLING 102(2021):13.