ROCHESTER, N.Y., March 6 (UPI) -- A lot can be learned about individuals from their interactions in online social media, even when they hide their messages and posts, U.S. researchers say.
In a study at the University of Rochester in New York, researchers said they were able to determine a person's location within a 100-yard radius with 85 percent accuracy by using only the location of that person's friends, a university release reported Tuesday.
They were also able to predict a person's Twitter friendships with high accuracy even when that person's profile was kept private, they said.
In one experiment, researchers studied the messages and data of heavy Twitter users from New York and Los Angeles to develop a computer model for determining human mobility and location.
The researchers tried to pinpoint their locations using only the information from their Twitter friends and in more than eight out of 10 instances successfully determined where the individuals lived to within one city block.
"Once you learn about relationships from peoples' tweets, it makes senses that you can track them," lead study author Adam Sadilek said. "My fiancee may be a good predictor of my location because we have breakfast together every morning."
In a reverse experiment, they used individuals' location data and the content of their tweets to predict people's Twitter friendships, or mutual following, and were successful 90 percent of the time.
"If people spend a lot of time together online and talk about the same things," Sadilek said, "they're more likely to be friends."