TY - JOUR T1 - Risk Premium of Social Media Sentiment JF - The Journal of Investing SP - 21 LP - 28 DO - 10.3905/joi.2017.26.3.021 VL - 26 IS - 3 AU - Patrick Houlihan AU - Germán G. Creamer Y1 - 2017/08/31 UR - https://pm-research.com/content/26/3/21.abstract N2 - 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 ER -