SAS and the United Nations Global Pulse have learned that social media chatter and conversation sentiment could warn of pending unemployment increases and inform policymakers of the likely effects.
Analyzing half a million blogs, forums and news sites, SAS Social Media Analytics and SAS Text Miner examined two years of social media data from the US and Ireland for references to unemployment and how people were coping. The analysis revealed that increased chatter about cutting back on groceries, increasing use of public transportation and downgrading one’s automobile could, indeed, predict an unemployment spike.
After a spike, surges in social media conversations about such topics as canceled vacations, reduced health care spending, and foreclosures or evictions shed light on lagging economic effects.
"Such information could be invaluable for policymakers trying to mitigate negative effects of increased unemployment," SAS said.
Meanwhile, the UN Global Pulse examined how new types of data complement and strengthen official statistics on how global crises affect people. Global Pulse is an innovation initiative of the UN Secretary-General, which functions as an innovation lab, bringing together expertise from inside and outside the United Nations to harness today's new world of digital data and real-time analytics for global development.
Using global social media as a new data source, both studies demonstrated how analyzing social media provides real-time feedback for policymakers and improves the ability to manage disruptive events.
“The private sector is analyzing this new data to understand its customers in real-time,” UN Secretary-General Ban Ki-moon said in a speech about Global Pulse to the UN General Assembly in November. “Much of this data contains signals that are relevant to development. We must use it to tell us what is happening, while it is happening.”
SAS said that in the US, a rise in "hostile" or "depressed" mood occurred four months before the unemployment spike, while increases in "anxious" unemployment chatter in Ireland correlated with an unemployment spike five months later. Increased "confused" chatter preceded the spike by three months, while "confident" chatter decreased significantly two months out.
A dashboard displayed results, including trends, moods on unemployment expressed in social media, mood change over time, and leading and lagging indicators of unemployment shocks.