Can Twitter analytics help sports gamblers perfect their bets? A new study from Carnegie Mellon University indicates that careful research of Twitter can beat the spread on NFL games. Researchers Christopher Dyer and Kevin Gimpel found that making bet decisions based on positive Twitter sentiment for hashtags such as #giants, #newyorkgiants, #steelers, and #steelersnation posted at least 12 hours prior to a game led to a 55% accuracy rate when betting with the spread.
Their gambling research is one of the first attempts to parse Twitter analytics to see how they apply to betting; while positive or negative online sentiment is commonly used to plot public relations strategies or evaluate entertainment products, relatively few gamblers turn to Twitter to influence their bets.
The pair will unveil their research on September 27 at the Machine Learning and Data Mining for Sports Analytics conference in Prague. But have they made bets using Twitter? “As far as I know, none of us has actually placed a bet based on our findings,” says Dyer.
[Image: Flickr user Thomas Schlosser]