Sentiment Risk Premia in the Cross-Section of Global Equity

This paper introduces a new sentiment-augmented asset pricing model and provides a com-prehensive understanding of the role of this sentiment-driven risk factors. We find that news andsocial media search-based indicators are significantly related to excess returns of internationalequity indices. Adding sentiment factors to both classical and more recent pricing models leadsto a significant increase in model performance. When it is estimated using the Fama-MacBethprocedure, our modified pricing model implies positive estimates of the risk premium for pos-itive sentiment and negative premia estimates for the negative sentiment factor. Our resultscontribute to the explanation of global cross-sectional average excess returns and are robust toaugmenting the model with fundamental factors, momentum, idiosyncratic volatility, skewness,kurtosis, and the returns on international currencies. When compared to competing definitionsof sentiment factors already popular in the literature, our new sentiment risk indicator turnsout to be superior in terms of out-of-sample predictive power