Sentiment risk premia in the cross-section of global equity

This paper applies a recently developed sentiment proxy to the construction of a new risk factor and provides a comprehensive understanding of its role in sentiment-augmented asset pricing models. We find that news and social media search-based indicators are significantly related to excess returns of international equity indices. Adding sentiment factors to both classical and more recent linear factor pricing models leads to a significant increase in their performance. When it is estimated using the Fama-MacBeth procedure, our sentiment-adjusted pricing model implies positive (negative) estimates of the risk premium for positive (negative) sentiment factors. We further differentiate between developed and emerging markets and uncover different patterns of return reversals / persistence in the long-term. Our results contribute to the explanation of global cross-sectional average excess returns and are robust to augmenting the model with fundamental factors, momentum, idiosyncratic volatility, skewness, kurtosis, and the returns on international currencies. When compared to competing definitions of sentiment factors popular in the literature, our novel sentiment risk variable turns out to be superior in terms of predictive power.