Abstract

This paper features an analysis of the relationship between the volatility of the Dow Jones Industrial Average (DJIA) Index and a sentiment news series using daily data obtained from the Thomson Reuters News Analytics (TRNA) provided by SIRCA (The Securities Industry Research Centre of the Asia Pacic). The expansion of on-line financial news sources, such as internet news and social media sources, provides instantaneous access to financial news. Commercial agencies have started developing their own filtered financial news feeds, which are used by investors and traders to support their algorithmic trading strategies. In this paper we use a sentiment series, developed by TRNA, to construct a series of daily sentiment scores for Dow Jones Industrial Average (DJIA) stock index component companies. A variety of forms of this measure, namely basic scores, absolute values of the series, squared values of the series, and the first differences of the series, are used to estimate three standard volatility models, namely GARCH, EGARCH and GJR. We use these alternative daily DJIA market sentiment scores to examine the relationship between financial news sentiment scores and the volatility of the DJIA return series. We demonstrate how this calibration of machine filtered news can improve volatility measures.

Additional Metadata
Keywords DJIA, Sentiment Scores, TRNA, Conditional Volatility Models
JEL Econometric Modeling: General (jel C50), Information and Market Efficiency; Event Studies (jel G14)
Publisher Tinbergen Institute
Persistent URL hdl.handle.net/1765/51088
Series Tinbergen Institute Discussion Paper Series
Citation
Allen, D.E, & Singh, A.K. (2014). Machine News and Volatility: The Dow Jones Industrial Average and the TRNA Sentiment Series (No. TI 2014-014/III). Tinbergen Institute Discussion Paper Series. Tinbergen Institute. Retrieved from http://hdl.handle.net/1765/51088