Using video recommendations data from more than 20,000 YouTube users, Mozilla researchers found that buttons like “not interested,” “dislike,” “stop recommending channel,” and “remove from watch history” are largely ineffective at preventing similar content from being recommended.
The report found that even at their best, these buttons still allow through more than half the recommendations identical to what users said they weren’t interested in. At their worst, the buttons barely dent in blocking similar videos.
Even when users tell YouTube they aren’t interested in certain types of videos, similar recommendations keep coming, a new study by Mozilla found.
Using data collected from over 500 million recommended videos, research assistants created over 44,000 pairs of videos — one “rejected” video plus a video subsequently recommended by YouTube. Researchers then assessed pairs or used machine learning to decide whether the recommendation was too similar to the video a user rejected.
Compared to the baseline control group, sending the “dislike” and “not interested” signals were only “marginally effective” at preventing harmful recommendations, containing 12 percent of 11 percent of bad requests, respectively. “Don’t recommend channel” and “remove from history” buttons were slightly more effective — they prevented 43 percent and 29 percent of harmful recommendations — but researchers say the tools offered by the platform are still inadequate for steering away unwanted content.
“YouTube should respect the feedback users share about their experience, treating them as meaningful signals about how people desire to spend their time on the platform,” researchers write.
To collect data from real videos and users, Mozilla researchers enlisted volunteers who used the foundation’s RegretsReporter. This browser extension overlays a general “stop recommending” button to videos viewed by participants.
In addition, users were randomly assigned a group on the back end, so different signals were sent to YouTube each time they clicked. For example, the button placed by Mozilla — dislike, not interested, don’t recommend channel, remove from history, and a control group for whom no feedback was sent to the platform.
Hernandez says Mozilla’s definition of “similar” fails to consider how YouTube’s recommendation system works. Hernandez says that the “not interested” option removes a specific video, and the “don’t recommend channel” button prevents the channel from being recommended in the future. The company says it doesn’t seek to stop recommendations of all content related to a topic, opinion, or speaker.
Besides YouTube, other platforms like TikTok and Instagram have introduced more and more feedback tools for users to train the algorithm, supposedly, to show them relevant content. But users often complain that similar recommendations persist even when flagging that they don’t want to see something. Moreover, it’s not always clear what different controls do, Mozilla researcher Becca Ricks says, and platforms aren’t transparent about how feedback is taken into account.
“I think that in the case of YouTube, the platform balances user engagement with user satisfaction. It is ultimately a tradeoff between recommending content that leads people to spend more time on the site and content the algorithm thinks people will like,” Ricks told. “The platform has the power to tweak which of these signals get the most weight in its algorithm, but our study suggests that user feedback may not always be the most important one.”