TY - JOUR
T1 - Leveraging Social Media to Predict Continuation and Reversal in Asset Prices
AU - Houlihan, Patrick
AU - Creamer, Germán G.
N1 - Publisher Copyright:
© 2019, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2021/2
Y1 - 2021/2
N2 - Using features extracted from StockTwits messages between July 2009 and September 2012, we show through simulations that: (1) message volume and sentiment can be used as a risk factor in an asset pricing model framework; (2) message volume and sentiment help explain the diffusion of price information over several days, and (3) message volume and sentiment can be used as features to predict asset price directional moves. Our findings suggest statistics derived from message volume and sentiment can improve asset price forecasts and leads to a profitable trading strategy.
AB - Using features extracted from StockTwits messages between July 2009 and September 2012, we show through simulations that: (1) message volume and sentiment can be used as a risk factor in an asset pricing model framework; (2) message volume and sentiment help explain the diffusion of price information over several days, and (3) message volume and sentiment can be used as features to predict asset price directional moves. Our findings suggest statistics derived from message volume and sentiment can improve asset price forecasts and leads to a profitable trading strategy.
KW - Computational finance
KW - Crowdsourcing
KW - Machine learning
KW - Sentiment analysis
KW - Social media
UR - http://www.scopus.com/inward/record.url?scp=85074861330&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074861330&partnerID=8YFLogxK
U2 - 10.1007/s10614-019-09932-9
DO - 10.1007/s10614-019-09932-9
M3 - Article
AN - SCOPUS:85074861330
SN - 0927-7099
VL - 57
SP - 433
EP - 453
JO - Computational Economics
JF - Computational Economics
IS - 2
ER -