homehome Home chatchat Notifications


How we get trapped in the same Youtube loops

Researchers try to untangle the twisted vines of Youtube suggestions.

Mihai Andrei
May 29, 2020 @ 10:10 pm

share Share

If you use Youtube a lot, you’ve probably come across this: the same suggestions pop again and again, and it often seems like we’re just trapped in a bubble.

The two main types of Youtube videos: popular, ‘bubbly’ videos (left), and diverse, exploratory videos (right).

Camille Roth, a researcher at the French National Centre for Scientific Research, studied something rather unusual in the world of science: Youtube. Or rather, Youtube’s recommendation algorithm.

Along with his colleagues, he explored recommendations from a thousand videos on different subjects — a total of half a million recommendations. They then compared how different videos sent the users on different paths, based on these video recommendations.

Illustration of the recursive recommendation structure of the Youtube videos. Credits: Roth et al.

Since almost 2 billion people use Youtube every month, the content recommendations that the site makes can have an effect on a large chunk of mankind. The popular belief is that Youtube — and social media, in general — tends to form confinement bubbles (or echo chambers).

In this case, the popular belief seems to be true.

While some social networks thrive on helping users find new types of content, that is not often the case on Youtube.

When researchers looked at the recommendation chains formed, they found that the Youtube algorithm often tends to confine people in the same bubbles, promoting the same type of content over and over again.

“We show that the landscape defined by non-personalized YouTube recommendations is generally likely to confine users in homogeneous clusters of videos. Besides, content for which confinement appears to be most significant also happens to garner the highest audience and thus plausibly viewing time.”

Example of video networks. Image credits: Roth et al.

It tends to work like this: when you watch a video, you essentially enter a network of interconnected videos that can serve as recommendations. Depending on which video you start with, the recommendation network is more or less closed — which leads to more similar or more different content.

In addition, the content that leads to the most confined recommendation networks also seem to revolve around the most viewed videos or the ones with the longest viewing time — in other words, the more popular a video is, the more likely it is to send you in a closed loop, which creates a self-enforcing mechanism.

“To simplify our findings very roughly and informally, let us say that there are two main stereotypes of YouTube videos: some with a high number of views, featuring loopy and not very diverse suggestions, and some with a low number of views, which generally feature more diverse and exploratory suggestions,” the researchers explain.

It’s important to keep note of this as you’re using Youtube, particularly if you’re watching polarizing or biased videos: the more you look at something, the likelier it is for the algorithm to suggest more similar things and reinforce the bias.

The study has been published in PLoS.

share Share

New Nanoparticle Vaccine Clears Pancreatic Cancer in Over Half of Preclinical Models

The pancreatic cancer vaccine seems to work so well it's even surprising its creators

Coffee Could Help You Live Longer — But Only If You Have it Black

Drinking plain coffee may reduce the risk of death — unless you sweeten it.

Scientists Turn Timber Into SuperWood: 50% Stronger Than Steel and 90% More Environmentally Friendly

This isn’t your average timber.

A Provocative Theory by NASA Scientists Asks: What If We Weren't the First Advanced Civilization on Earth?

The Silurian Hypothesis asks whether signs of truly ancient past civilizations would even be recognisable today.

Scientists Created an STD Fungus That Kills Malaria-Carrying Mosquitoes After Sex

Researchers engineer a fungus that kills mosquitoes during mating, halting malaria in its tracks

From peasant fodder to posh fare: how snails and oysters became luxury foods

Oysters and escargot are recognised as luxury foods around the world – but they were once valued by the lower classes as cheap sources of protein.

Rare, black iceberg spotted off the coast of Labrador could be 100,000 years old

Not all icebergs are white.

We haven't been listening to female frog calls because the males just won't shut up

Only 1.4% of frog species have documented female calls — scientists are listening closer now

A Hawk in New Jersey Figured Out Traffic Signals and Used Them to Hunt

An urban raptor learns to hunt with help from traffic signals and a mental map.

A Team of Researchers Brought the World’s First Chatbot Back to Life After 60 Years

Long before Siri or ChatGPT, there was ELIZA: a simple yet revolutionary program from the 1960s.