By tracking how quickly a photo is shared, scientists have been able to develop a computer algorithm that predicts the possibility of a picture going viral on Facebook, Press Trust of India reported.
The hints to predicting which of the millions of photos on Facebook will manage to rise from obscurity and go viral lie in "cascades."
The term "cascades" is used to describe photos or videos being shared multiple times, according to PTI.
"It wasn't clear whether information cascades could be predicted because they happen so rarely," said Jure Leskovec, assistant professor of computer science.
Only 1 in 20 photos posted on Facebook gets shared even once, according to data provided by Facebook scientists in a recent collaboration with university scientists. In addition, only 1 in 4,000 gets more than 500 shares per picture.
"In a paper to be presented at the International World Wide Web Conference in Seoul, Korea, the researchers will describe how they accurately predicted, 8 out of 10 times, when a photo cascade would double in shares; that is, if a photo got 10 shares, would it get 20? If it got 500, would it reach 1,000, and so on?" PTI reported.
The project was started by analyzing 150,000 Facebook photos, each of which had been shared at least five times. In order to protect privacy, names and identifiers were removed from the data.
The team included Leskovec, Stanford doctoral student Justin Cheng, Facebook researchers Lada Adamic and P Alex Dow, and Cornell University computer scientist Jon Kleinberg.
"A preliminary analysis of those photos revealed that, at any given point in a cascade, there was a 50-50 chance that the number of shares would double," PTI reported. "The scientists then looked for variables that might help them predict doubling events more accurately than a coin toss, including the rate and speed at which photos were shared, and the structure of sharing (photos re-posted in multiple networks proved to create stronger cascades)."
PTI added, "After factoring several criteria into their analysis the computer scientists were able to accurately predict doubling events almost 80 per cent of the time."
"Slow, persistent cascades don't really double in size," Leskovec said.
