LAUSR

Abstract The authors explore the interaction between media content and market returns and volatility. They utilize propriety investor sentiment measures developed by Thompson Reuters MarketPsych. The data are from a commercial-strength comprehensive textual analysis that provides 24-hr rolling average scores of total references in the news and social media by counting overall positive references net of negative references. The authors select 4 measures of investor sentiment that reflect both pessimism and optimism of small investors. These measures are fear, gloom, joy, and stress. The objective is twofold. First, the authors examine the ability of these sentiment measures to predict market returns. Second, they are interested in exploring the effects of these sentiment measures on market return and volatility. For this purpose, the authors utilize threshold generalized autoregressive conditional heteroskedasticity models. They explore the ability of sentiment measures to predict both the level of and change in market returns. The sentiment measure of stress has a small effect on the market return for a 1-day lag. The other 2 sentiment measures, gloom and joy, seem to play no role in predicting market returns. Furthermore, the authors find that fear among investors has a major and lasting effect on market returns and conditional volatility.