Risk Premium of Social Media Sentiment

Abstract

This research investigates the predictive capability of sentiment extrapolated from three dictionaries: financial, social media, and mood states. The findings show that 1) through the Fama–MacBeth regression method, social media–based sentiment measures can be used as risk factors in an asset pricing framework; 2) these sentiment measures have predictive capability when used as features in a machine learning framework, and 3) adjusting returns for market effects results in positive alpha.

TOPICS: Security analysis and valuation, factor-based models