Archived | Event | Seminar Series | Statistics and Data Science in the Digital Age

What’s the value of Artificial Synthetic Data?
19 April, 2017
Computer with data on the screen
Does your organisation need help with data?
27 April, 2017
Show all

Archived | Event | Seminar Series | Statistics and Data Science in the Digital Age

Session Seven – Forecasting with Social Media: Evidence from Tweets on Soccer Matches

Archived – Please note this event series took place in the past and has been left here for reference purposes. View our full list of events to see what we have coming up or send us an email if there is a particular type of event you are interested in.

Date: Friday 5 May 2017
Time: 14:00
Venue: S2.15 (D’Arcy Thompson Room), University of East Anglia
Speaker: Dr Alasdair Brown (ECO)

Social media content – for example that produced on Twitter or Facebook – is increasingly used as a forecasting tool. For example, Hollywood studios use data from social media to forecast demand for new films. Financial firms extract sentiment from Twitter to predict stock returns, and design funds to algorithmically trade based on this information. And social media is now even used for economic forecasting: in 2012, the Australian Treasury department launched a division to harness social media data to forecast workforce participation and retail sentiment, among other things.

But how useful and accurate a forecasting tool is social media? In this paper we evaluate the accuracy of social media forecasting in a fast-moving, high-profile environment: English Premier League soccer matches. We study 13.8 million Tweets, an average of 5.2 Tweets per second, during 372 matches that took place during the 2013/14 season. Our primary aim is assess whether information contained in these Tweets can predict match outcomes.

We find that Twitter activity does indeed predict match outcomes, even after controlling for contemporaneous betting/prediction market prices. Twitter activity is particularly useful in the aftermath of a significant event (e.g. a goal or red card), suggesting that social media aids in the interpretation of information. While some of the forecasting capacity is tied up with individual participants, e.g. BBC journalists, the aggregate tone of all Tweets is also informative. Further tests reveal that social media content is useful in forecasting outcomes, in part, because it is an effective mechanism for harnessing the ‘wisdom of crowds’ (Galton, 1907, Surowiecki, 2005).

Tea and coffee will be provided after the talk.

If you would like more information, or to discuss the seminar series further, please contact the organisers: Prof. Elena Kulinskaya and/or Prof. Peter Moffatt