Study leader Saeideh Bakhshi, a doctoral candidate at the Georgia Institute of Technology College of Computing, adviser Eric Gilbert, an assistant professor in the School of Interactive Computing, and David Shamma, a Yahoo research scientist, looked at 1.1 million photos on Instagram, using face detection software.
They found not only did photos with faces produce more likes, the posts with pictures of faces were 32 percent more likely to attract comments.
The researchers also found the number of faces in the photo, the age or gender made no difference. On average, pictures of children or teenagers were no more popular than those of adults, even though Instagram is most popular among younger people. The study also noticed that men and women have the same chances of getting likes or comments.
However, a few factors did play a role. As expected, people with more followers attracted more engagement -- but only if it wasn't overdone.
"The more you post, the less feedback you're going to get," Bakhshi said in a statement. "Posting too much decreases likes two times faster than comments."
Bakhshi also said the more photos a person uploads, the lower the probability any single one has of getting likes or comments.
Gilbert noted social media sites such as Flickr or Pinterest could increase their search ranking and keep consumers onsite and active by featuring human faces in their online content.
"Designers could also use this knowledge to quickly filter, prioritize and highlight photos shared by followers," Gilbert said. "Especially pictures that have just been submitted and haven't had enough time to pick up very many likes or comments yet."
The paper is scheduled to be presented April 26 to May 1 in Toronto at the ACM CHI Conference on Human Factors in Computer Systems.