Abstract
Information extracted from social media has been used by academics, and increasingly by practitioners, to predict stock returns. But to what extent does social media output predict asset fundamentals, and not simply short-term returns? In this paper we analyse 13.8m posts on Twitter, and high-frequency betting data from Betfair, concerning English Premier League soccer matches in 2013/14. Crucially, asset fundamentals are revealed at the end of play. We find that the Tweets of certain journalists, and the tone of all Tweets, contain fundamental information not revealed in betting prices. In particular, Tweets aid in the interpretation of news during matches.
Original language | English |
---|---|
Pages | 1-33 |
Number of pages | 33 |
Publication status | Published - 25 Aug 2016 |
Event | EEA-ESEM 2016 Conference: 31th annual congress of the European Economic Association & 69th European meeting of the Econometric Society - University of Geneva, Geneva, Switzerland Duration: 22 Aug 2016 → 26 Aug 2016 |
Conference
Conference | EEA-ESEM 2016 Conference |
---|---|
Country/Territory | Switzerland |
City | Geneva |
Period | 22/08/16 → 26/08/16 |
Keywords
- social media
- prediction markets
- fundamentals
- sentiment
- mispricing
ASJC Scopus subject areas
- Economics, Econometrics and Finance(all)
- Economics and Econometrics
- Finance