Facebook Posts May Predict Unemployment Trends


NEW YORK (MainStreet) — Can social chatter point economists to an uptick in the unemployment rate? A social media consulting firm that measured hundreds of thousands of social network users says that's the case – and it has the data to prove it.

Social media remains the fastest-growing component of that global behemoth known as the World Wide Web. According to the technology analytical firm GlobalWebIndex, 59% of all Internet users engage in social networking, up from 36% when the firm began tracking social networking behavior in 2009.

Twitter seems to be the fastest-growing social media segment, growing to 24% from 13%, while uploading video rose to 27% from 21%, GlobalWebIndex reports. Blog writing, incidentally, is leveling off, the report adds.

Now it seems, the data on social media, and how it affects society, is peeling back attitudes few could have predicted even five years ago. A great example comes in a study from SAS and United Nations Global Pulse called Unemployment Through the Lens of Social Media.

In it, study researchers track the social media chatter of hundreds of thousands of Internet users in the U.S. and Ireland and arrive at an interesting conclusion: You can pretty much nail unemployment spikes based on what users are saying to each other on social networks.

SAS, the data and software company that led the study, measured what it calls “mood scores” and conversation volumes and matched them with actual unemployment figures to see if an uptick in chatter about household budgets, careers, jobs and layoffs was indicative of a similar upward spike in the jobless rate.

“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,” the report says. “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 says its “mood score” is based on tones and emotions displayed by social media users. For instance, the study says an upward spike in “anxious” unemployment chatter with terms such as “car repossessed” or “entering foreclosure” often translates into a higher unemployment rate four months later in the U.S., with the same result five months later in Ireland.

Ironically, information culled from online resources is just an extension of what economists have always used to formulate cultural forecasts – and it could go way beyond the unemployment picture.

“Social media and Internet content is like the letters and phone calls that have always informed organizations,” says I-sah Hsieh, global manager of International Development at SAS. “Only now it’s digital, public and massive in scale. This untapped treasure can provide real-time feedback on policies, improve public safety, enhance citizen relations and support important sociological research.”

So the next time you log on to Facebook or Twitter, and up pops a note from a cousin or a friend on how their household budgets are tightening or how their workload grows even more burdensome at work, take note – conversations such as those could be an early indicator of impending job losses.

Show Comments

Back to Top