Forecasting viral videos on the Internet is possible based on new research that aims to examine how people spend time watching videos online.
To know if viral videos are possible to forecast, Stanford University neuroscientist Brian Knutson and colleagues studied the approach called neuroforecasting.
This refers to a process in which brain data from individuals who make decisions to predict how bigger groups of unrelated people will respond to the same choices is examined.
The study “Brain activity forecasts video engagement in an internet attention market” found that neural and behavioral responses to a video could forecast how long others will continue watching the same video online.
"In many of our lives, every day, there is often a gap between what we actually do and what we intend to do," said Knutson, who is a professor of psychology in the School of Humanities and Sciences, reflecting on his smartphone habits.
"We want to understand how and why people's choices lead to unintended consequences -- like wasting money or even time -- and also whether processes that generate individual choice can tell us something about choices made by large groups of people."
Together with other researchers at Stanford’s Graduate School of Business, Knutson scanned people’s brains as they picked and viewed videos. They probed data from 36 participants while being scanned under the brain imaging technique called fMRI.
Hidden information
Published in the journal Proceedings of the National Academy of Sciences, the study also described participants' behavior.
The viewers were asked questions about the video, like how it made them feel and if they believe it would become popular.
Then, the researchers monitored the same videos shown on the Internet in terms of daily views and average duration of viewings.
"Here, we have a case where there is information contained in subjects' brain activity that allows us to forecast the behavior of other, unrelated, people -- but it's not necessarily reflected in their self-reports or behavior," explained Lester Tong, a graduate student in the Knutson lab.
"One of the key takeaways here is that brain activity matters, and can even reveal hidden information."
Knutson and his colleagues discovered that longer video views were linked to the movement in the reward-sensitive regions of the brain.
They also noted the association between shorter video views and activity in regions sensitive to arousal or punishment.
