News and Social Media Emotions in the Commodity Market
Review of Behavioral Finance, Forthcoming
30 Pages Posted: 11 May 2017
Date Written: February 24, 2017
Emotion plays a significant role in both institutional and individual investors’ decision making process. However, there is a lack of empirical evidence available that addresses how investors’ emotions affect commodity market returns. This study examines the short-term predictive power of media-based emotion indices on the following five days’ commodity returns. The research adopts a proprietary dataset of commodity specific market emotions, which is computed based on a comprehensive textual analysis of sources from newswires, Internet news sources, and social media. Time series econometrics models (Threshold-GARCH and VAR) are employed to analyze fourteen years (01/1998-12/2011) of daily observations of the CRB commodity market index, crude oil and gold returns, and the market-level sentiment and emotions (optimism, fear, and joy).
The empirical results suggest that the commodity specific emotions (optimism, fear, and joy) have significant influence on individual commodity returns, but not on commodity market index returns. Additionally, the research findings support the short-term predictability of the commodity specific emotions on the following five days’ individual commodity returns. Compared to the previous studies of news sentiment on commodity returns (Borovkova, 2011; Borovkova and Mahakena, 2015; Smales, 2014), our research provides further evidence of the effects of news and social media based emotions (optimism, fear and joy) in the commodity market. Additionally, we propose that market emotion incorporates both a sentimental effect and appraisal effect on commodity returns. Empirical results are shown to support both the sentimental effect and appraisal effect when market sentiment is controlled in crude oil and gold spot markets.
Keywords: Commodity, Investor Emotion, NeuroFinance, TRMI
JEL Classification: C22, D80, D87, G13
Suggested Citation: Suggested Citation