28 Pages Posted: 19 Apr 2017
Date Written: April 17, 2017
The nature of the interaction between news and market events has long been speculated and inquired upon by both practitioners and academics. To investigate the complex interactions between these events, we employ a multivariate Hawkes (M-variate Hawkes) process to evaluate dynamic effects among the four types of distinct events: the positive return event, negative return event, the positive sentiment event and negative sentiment event. Using both intraday S&P 500 return data and Thomson Reuters News sentiment data from 2008 to 2014, we find: a) self-excitation is strong for all four types of events at 15 minutes time scale. b) there is a significant mutual-excitation between positive return and positive sentiment, and negative return and negative sentiment. c) decaying speed of return events is almost twice as faster as that of sentiment events, which means market prices move faster than investor sentiment changes. d). positive sentiment shocks tend to generate negative price jumps, and the cross-excitation between positive and negative sentiment is even stronger than their self-excitation of these sentiment events. To our best knowledge, this is the first paper to examine the market return and investor sentiment interactions at relatively high frequency. These findings provide new insights for both academic researchers and practitioners to better understand the cascading effects of extreme returns and elevated investor sentiment.
Keywords: Point Process; Hawkes Process; Investor Sentiment; Return Jumps; News Sentiment
JEL Classification: C32; C51; G14; G17
Suggested Citation: Suggested Citation
Yang, Steve Y. and Liu, Anqi and Chen, Jing and Hawkes, Alan G, Applications of a Multivariate Hawkes Process to Joint Modeling of Sentiment and Market Return Events (April 17, 2017). Available at SSRN: https://ssrn.com/abstract=2954079 or http://dx.doi.org/10.2139/ssrn.2954079