Social media at first seemed like a gold mine of data for behavioral scientists wanting to understand what makes people do what they do.
But computer scientists at Carnegie Mellon University and McGill University say the massive datasets mined from social media sites may be misleading.
In the journal Science, Carnegie Mellon’s Juergen Pfeffer and McGill’s Derek Ruths say researchers need to find ways of correcting for the biases in the information gathered from Twitter and other social media.
Pfeffer and Ruths say thousands of research papers each year are now based on data gleaned from social media, a source of data which barely existed even five years ago.
“Not everything that can be labeled as Big Data is automatically great,” Pfeffer says.
Many think, or hope, that if they gather a large enough data they can overcome any biases or distortion which might lurk there.
“But the old adage of behavioral research still applies: Know Your Data,” he says.
Following the Boston Marathon bombing in 2013, for example, Pfeffer collected 25 million related tweets in just two weeks.
“You get the behavior of millions of people — for free,” he says.
But despite researchers’ attempts to generalise study results to a broad population, social media sites often have substantial population biases.
Instagram has special appeal to adults between the ages of 18 and 29, African-Americans, Latinos, women and urban dwellers.
Pinterest is dominated by women between the ages of 25 and 34 with average household incomes of $100,000.
Yet Ruths and Pfeffer say researchers seldom acknowledge these built-in sampling biases.
Other questions about data sampling may never be resolved because social media sites use proprietary algorithms to create or filter data streams and those algorithms are subject to change without warning.
And sometimes not all “people” on these sites are ordinary people.
Some are professional writers or public relations experts who post on behalf of celebrities or corporations.
And “followers” can be bought even as social media sites try to hunt down and eliminate bogus accounts.
Business Insider Emails & Alerts
Site highlights each day to your inbox.