A browser extension for users to gain back control over their YouTube recommendations
Project Information
- Project ID
- ledger_YouChoose
- Contact
- marcfaddoul@berkeleyedu
- Countries
- france
Related Products
Software or product(s) created or improved through this project
Additional Information
Recommender systems are the gateway to most of the content consumed on social media These algorithms are opaque not customizable and designed to maximize advertising revenues rather than the interests of the users On YouTube in particular 70% of the content watched is suggested by an algorithmWe develop a browser extension which enables users to customize filter and enhance their recommendations when they visit YouTubecomOur core design values is to provide customizable transparent AI trained on reliable and explicit human feedback generated by our user-communityAs an initial feature the tool lets users filter-out unworthy clickbait content With the extension downloaded users see a button to flag content that they deem unworthy (clickbait) and the content that they like best (time well spent)These evaluations are then used to train our machine learning model in order to evaluate new content at scale and to foster trusted decentralized community of content reviewers
End-User Relevance
A browser extension for users to gain back control over their YouTube recommendations
Endorsements
http://algotransparency.org
Disclaimer: We provide transparency on YouTube's algorithms
Community Discussion 3 comments
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident.
Sunt in culpa qui officia deserunt mollit anim id est laborum. Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium.