London, Oct 14 (PTI) The tone of Twitter posts can helppredict the result of football matches when combined withbetting market prices, a study has found.
Twitter activity can predict when a team is more likelyto win and soccer bets are mispriced, according toresearchers from University of East Anglia (UEA) in the UK.
The study, published in the journal Economic Inquiry,examined 13.8 million tweets - an average of 5.2 tweets persecond - during an English Premier League (EPL) season.
These were compared with in-play betting prices availableat the same time on online betting exchange Betfair.
They found that if the combined tone of tweets in a givensecond during a match was positive - as measured by a micro-blogging dictionary - then the team was more likely to winthan the betting market prices implied.
Tweets were particularly informative in the aftermath ofgoals and red cards, suggesting that social media content isparticularly useful in assessing the implications andsignificance of new information.
Social media is used as a forecasting tool by a varietyof firms and agencies, but the researchers wanted to find outhow useful and accurate it is.
They measured the aggregate tone of all tweets for eachteam, in each second of 372 matches that took place duringthe 2013/14 season.
"We find that Twitter activity predicts match outcomes,after controlling for betting market prices," said AlasdairBrown, of UEA's School of Economics.
"Much of the predictive power of social media presentsitself just after significant market events, such as goalsand red cards, where the tone of Tweets can help in theinterpretation of information.
"In short, social media activity does not just representsentiment or misinformation. If sensibly aggregated it can,when combined with a prediction market, help to improveforecast accuracy," said Brown.
The researchers constructed a number of bettingstrategies to quantify the degree of mispricing that socialmedia predicts.
Using conservative estimates of the commission paid toBetfair, and a strategy of betting when Tweets on a team arepositive, a bettor could have earned an average return of2.28 per cent from 903,821 bets.
This compares favourably with average returns of 5.41 percent across the matches studied. PTI SARSAR.
This is unedited, unformatted feed from the Press Trust of India wire.