Welcome to RS_c, the central platform for the RecSys community. We provide curated lists of recommender-systems datasets, algorithms, books, conferences and many resources more. Maybe most importantly, we publish the latest recommender-system news. If you want your news to be reported on RS_c, read here.
YouTube changes content recommendations to enhance ‘Teen Wellbeing’
November 4, 2023
James Beser, Director of Product Management YouTube Kids and Youth, reports that YouTube has updated its recommender system to better cater to the needs of teenagers, with a focus on safety, privacy, and wellbeing. James also reports that YouTube is introducing new partnerships with experts in youth, parenting, and mental health to enhance the experience for this age group.
According to their blog post, YouTube consulted with the Youth and Families Advisory Committee, composed of experts in various fields, to understand how online content affects teen development. They’ve learned that repetitive content portraying idealized standards can impact teens’ self-perception.
Based on these insights, YouTube implemented additional controls to limit recommendations of potentially harmful content to teens. This includes content that idealizes certain body types or behaviors, and displays of social aggression.
YouTube is also revising features like ‘Take a Break’ and ‘Bedtime’ reminders, making them more noticeable and frequent for viewers under 18. These features will interrupt viewing with full-screen messages, reminding users to take breaks at set intervals.
A new update expands crisis resource panels for users searching for sensitive topics. This includes a full-page experience that offers support and redirects users to positive content, designed in consultation with experts in crisis prevention.
YouTube is collaborating with WHO and Common Sense Networks to create resources that help teens and their families engage in safe online practices and responsible content creation. This initiative aims to encourage thoughtful online behavior and peer connection through content.
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries.
We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).