• While YouTube is the second most visited website in the world, the pressure is getting more real as it faces competition from other Apps.
YouTube introduced a “recommendations” feature recently for viewers dissatisfied with the videos the platform has recommended to them.
By pressing the “dislike” button the user indicates that he or she would not want to watch similar videos but reports state that the button may not make a big difference.
While YouTube is the second most visited website in the world, the pressure is getting more real as it faces competition from other applications that still want to look like they are relevant.
In support of this, recent research by Mozilla, the foundation behind the Firefox web browser, buttons like “not interested,” “dislike,” “stop recommending channel,” and “remove from watch history” are largely ineffective at preventing similar content from being recommended.
The study analysed more than 567 million YouTube video recommendations with the help of 22,700 participants.
The researchers used a tool called, Regret Reporter, which Mozilla developed to study YouTube’s recommendation algorithm.
It collected data on participants’ experiences on the platform.
Results
The researchers found that “Don’t recommend channel” and “remove from history” buttons were slightly more effective as they prevented 43 per cent and 29 per cent of bad recommendations.
Sending the “dislike” and “not interested” signals were only “marginally effective” at preventing bad recommendations, preventing 12 per cent of 11 per cent of bad recommendations, respectively.
Researchers suggested that 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 want to spend their time on the platform,” researchers wrote on Tuesday.
“Yes they did change, but in a bad way. In a way, I feel punished for proactively trying to change the algorithm's behavior. In some ways, less interaction provides less data on which to base the recommendations.” (Survey ID112) wrote.