Demonstrating the power of social media, a number of photos on Facebook have sprung from almost obscurity to being viral. These photos include ones that anyone would predict to go viral, such as that by Barack Obama to that of a house built in the pristine blue-green sea near a sea shore. So there is almost no predictability as to which photo will go viral. But by studying "cascades," the term used to describe photos or videos being shared multiple times, Stanford scientists have found some clues regarding this phenomenon.

According to the statistics shared by Facebook scientists with university researchers in a recent collaboration, only 1 in 20 photos gets shared even more than once. Similarly, only 1 in 4,000 gets more than 500 shares, hardly any number to be classified as viral, but enough to give an idea regarding the probability of a photo being shared more than a million times. The scientists were given the task of predicting the probability of whether a photo cascade will double in shares or not; that is, if a photo got 10 shares, would it get 20? If it got 500, would it reach 1,000, and so on. The team investigating this comprised of researchers Stanford Computer Science Assistant Professor Jure Leskovec, Stanford doctoral student Justin Cheng, Facebook researchers Lada Adamic and P. Alex Dow, and Cornell University computer scientist Jon Kleinberg.
The rate of sharing or cascade for an image/video was tested by the scientists. Nearly 150,000 Facebook photos, each of which had been shared at least five times were analysed. The privacy-sensitive data of these images was removed. According to the preliminary analysis, at any given point in a cascade, there was a 50-50 chance that the number of shares would double. The scientists then went out to look for the variables which would help them predict the doubling rate more accurately. These panned out to be the rate and speed at which photos were shared, and the structure of sharing since photos reposted in multiple networks proved to create stronger cascades.

Thus, the scientists ended up being correct about 80 percent of times whether the cascade number would double or not. Their algorithm became more accurate the more times a photo was shared, predicting 88% times correctly when a photo was shared hundreds of times. The researchers also concluded that the speed of sharing was the best predictor of cascade growth because by simply analyzing how quickly a cascade unfolded predicted doublings 78 percent of the time. Also, the structure of the sharing network mattered as to the outcome of a cascade doubling.

There seems to be no magic formula as to make a photo/video more share-able, but, a combination of a right network, a right time and right speed could do the trick.

For 17 most viral photos on Facebook, click The 20 Most Popular Photos.

Source: #-Link-Snipped-#