YouTube’s ‘dislike’ barely works, according to new study on recommendations

If you’ve ever felt that it’s difficult to get YouTube’s algorithm to stop suggesting a certain video type once it slips into your recommendations, you’re not alone. In fact, getting YouTube to accurately understand your preferences can be even harder than you think. A major problem, according to Mozilla, is that YouTube’s in-app controls, such as the “Dislike” button, are largely ineffective as a tool for controlling suggested content. According to the report, “these buttons prevent less than half of unwanted algorithmic recommendations.”

Researchers at Mozilla used data collected by RegretsReporter, its browser extension that allows people to share their recommendation data for use in studies like this one. Overall, the report drew on millions of featured videos, as well as anecdotal accounts from thousands of people.

Mozilla tested the effectiveness of four different controls: the thumbs-down button Dislike, Not Interested, Do Not Recommend Channel, and Remove from Watch History. Researchers found these varied in effectiveness, but the overall effect was “small and insufficient.”

Of the four controls, “Do not recommend by channel” was the most effective, preventing 43 percent of unwanted recommendations, while “Not interested” was the least effective, preventing only about 11 percent of unwanted suggestions. The “Dislike” button was almost the same at 12 percent, and “Remove from watch history” eliminated about 29 percent.

In their report, the Mozilla researchers noted the great efforts that study participants would sometimes make to prevent unwanted recommendations, e.g. B. Watching videos while logged out or connected to a VPN. The researchers say the study highlights the need for YouTube to better explain its controls to users and give people more proactive ways to define what they want to watch.

“YouTube and many other platforms work by relying on passive data collection to make inferences about your preferences,” says Becca Ricks, a senior researcher at Mozilla who co-authored the report. “But it’s a bit of a paternalistic way of working, where you sort of make decisions on behalf of the people. You could ask people what they want to do on the platform instead of just watching what they do.”

Mozilla’s research comes amid increasing demands for major platforms to be more transparent about their algorithms. In the United States, lawmakers have proposed bills to make recommendation algorithms too “opaque” and to pin companies down for algorithmic bias. The European Union is even further. The recently passed Digital Services Act will require platforms for how recommendation algorithms work and open them up to external researchers.

All products recommended by Engadget are selected by our editorial team independently from our parent company. Some of our stories contain affiliate links. If you buy something through one of these links, we may receive an affiliate commission. All prices are correct at time of publication. YouTube’s ‘dislike’ barely works, according to new study on recommendations

Russell Falcon is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – The content will be deleted within 24 hours.

Related Articles

Back to top button