PT - JOURNAL ARTICLE AU - Patrick Houlihan AU - Germán G. Creamer TI - Risk Premium of Social Media Sentiment AID - 10.3905/joi.2017.26.3.021 DP - 2017 Aug 31 TA - The Journal of Investing PG - 21--28 VI - 26 IP - 3 4099 - https://pm-research.com/content/26/3/21.short 4100 - https://pm-research.com/content/26/3/21.full AB - 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