RT Journal Article
SR Electronic
T1 Risk Premium of Social Media Sentiment
JF The Journal of Investing
FD Institutional Investor Journals
SP 21
OP 28
DO 10.3905/joi.2017.26.3.021
VO 26
IS 3
A1 Patrick Houlihan
A1 Germán G. Creamer
YR 2017
UL https://pm-research.com/content/26/3/21.abstract
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