Forecasting with Social Media: Evidence from Tweets on Soccer Matches

Alasdair Brown; Dooruj Rambaccussing; J. James Reade; Giambattista  Rossi

doi:10.1111/ecin.12506

Forecasting with Social Media: Evidence from Tweets on Soccer Matches

Alasdair Brown (Lead / Corresponding author), Dooruj Rambaccussing, J. James Reade, Giambattista Rossi

University of Dundee School of Business

Research output: Contribution to journal › Article

10 Citations (Scopus)

81 Downloads (Pure)

Abstract

Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8m posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a micro-blogging dictionary to analyse the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards.

Original language	English
Pages (from-to)	1748-1763
Number of pages	16
Journal	Economic Inquiry
Volume	56
Issue number	3
Early online date	12 Oct 2017
DOIs	https://doi.org/10.1111/ecin.12506
Publication status	Published - Jul 2018

Keywords

forecasting
social media
prediction markets
wisdom of crowds
soccer

Access to Document

10.1111/ecin.12506

Author Accepted Manuscript
This is the peer reviewed version of the following article: Brown, A., Rambaccussing, D., Reade, J. J. and Rossi, G. (2017), FORECASTING WITH SOCIAL MEDIA: EVIDENCE FROM TWEETS ON SOCCER MATCHES. Econ Inq. doi:10.1111/ecin.12506, which has been published in final form at [Link to final article using the DOI]. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.
Accepted author manuscript, 710 KB

Fingerprint Dive into the research topics of 'Forecasting with Social Media: Evidence from Tweets on Soccer Matches'. Together they form a unique fingerprint.

Profiles

Rambaccussing, Dooruj

University of Dundee School of Business - Lecturer (Teaching and Research)

Person: Academic

Cite this

Brown, A., Rambaccussing, D., Reade, J. J., & Rossi, G. (2018). Forecasting with Social Media: Evidence from Tweets on Soccer Matches. Economic Inquiry, 56(3), 1748-1763. https://doi.org/10.1111/ecin.12506

@article{28c43d3f9684420db5ece77accb716dd,

title = "Forecasting with Social Media: Evidence from Tweets on Soccer Matches",

abstract = "Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8m posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a micro-blogging dictionary to analyse the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards.",

keywords = "forecasting, social media, prediction markets, wisdom of crowds, soccer",

author = "Alasdair Brown and Dooruj Rambaccussing and Reade, {J. James} and Giambattista Rossi",

note = "British Academy. Grant Number: SG140097; Twitter through their #DataGrants scheme; Oxford Martin School (OMS); Reade thanks the Open Society Foundations (OSF); SIRE Early Career Grant; British Academy and the Leverhulme Trust. Grant Number: SG14009",

year = "2018",

month = jul,

doi = "10.1111/ecin.12506",

language = "English",

volume = "56",

pages = "1748--1763",

journal = "Economic Inquiry",

issn = "0095-2583",

publisher = "Wiley",

number = "3",

}

TY - JOUR

T1 - Forecasting with Social Media

T2 - Evidence from Tweets on Soccer Matches

AU - Brown, Alasdair

AU - Rambaccussing, Dooruj

AU - Reade, J. James

AU - Rossi, Giambattista

N1 - British Academy. Grant Number: SG140097; Twitter through their #DataGrants scheme; Oxford Martin School (OMS); Reade thanks the Open Society Foundations (OSF); SIRE Early Career Grant; British Academy and the Leverhulme Trust. Grant Number: SG14009

PY - 2018/7

Y1 - 2018/7

N2 - Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8m posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a micro-blogging dictionary to analyse the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards.

AB - Social media is now used as a forecasting tool by a variety of firms and agencies. But how useful are such data in forecasting outcomes? Can social media add any information to that produced by a prediction/betting market? We source 13.8m posts from Twitter, and combine them with contemporaneous Betfair betting prices, to forecast the outcomes of English Premier League soccer matches as they unfold. Using a micro-blogging dictionary to analyse the content of Tweets, we find that the aggregate tone of Tweets contains significant information not in betting prices, particularly in the immediate aftermath of goals and red cards.

KW - forecasting

KW - social media

KW - prediction markets

KW - wisdom of crowds

KW - soccer

U2 - 10.1111/ecin.12506

DO - 10.1111/ecin.12506

M3 - Article

VL - 56

SP - 1748

EP - 1763

JO - Economic Inquiry

JF - Economic Inquiry

SN - 0095-2583

IS - 3

ER -