• by Erik Sass , Staff Writer @eriksass1, December 30, 2014

One of the world’s oldest and most respected financial institutions, the Bank of England, is embracing social media as a tool for gathering information about a range of economic indicators, according to Sky News, which first reported the news. The social media initiative is part of a larger “Big Data” push aimed at measuring and predicting economic activity more precisely, in order to set interest rates more effectively.

The BoE will analyze a range of data including social media sentiment and online discussion of things such as consumption behaviors and travel, as well as job searches, online prices, and other relevant factors. The Bank is also integrating data from more traditional sources like mortgage databases into the new analytical models, according to chief economist Andy Haldane.

Haldane told Sky News: “Official statistics tend to be lagging and tend to be revised. And what this scraping of the web can do is give us a better today read on what's going on.” He added that “informal sources… have been somewhat more reliable in picking up the uptick in the fortunes of the economy.”

Economists have been studying social media’s predictive capacities for at least a few years. Back in 2012 I wrote about a study by SAS and UN Global Pulse, a UN think tank, which demonstrated that social media can be used to predict unemployment trends, giving an early warning of economic downturns. The study drew on social media conversations in the U.S. and Ireland from June 2009-June 2011.

The researchers examined online job-related conversations from blogs, forums and news in the U.S. and Ireland (which suffered one of the steepest economic downturns in the developed world) and assigned a quantitative “mood score” based on the tone of the conversations. The researchers found that the volume of conversations showing a “confused” mood correlated with an uptick in unemployment three months later. Likewise, conversations about public transportation spiked about a month before unemployment.