Researchers at the University of New South Wales and Microsoft presented a paper at the Symposium on the Dynamics of the Internet and Society that illustrates the ways in which big data sets can fail scientists, especially when they are used to make claims about people's behavior.
"There's been the emergence of a philosophy that big data is all you need," says New South Wales associate professor Katie Crawford. "We would suggest that, actually, numbers don't speak for themselves."
For example, researchers often use Facebook to analyze people's social relationships. However, Facebook can show a distorted picture of people's closest social relationships, such as with parents, live-in romantic partners, or friends seen daily.
The researchers' work shows that studying large data still requires finesse. For example, Twitter can lead to problems for researchers because about 40 percent of Twitter's active users sign in to listen, not to post, which suggests that posts could come from a certain type of person, instead of a random sample, according to Crawford. Studying data from different sources also can lead to unexpected results for the people involved, she notes.
From Technology Review
View Full Article