An update to dislikes on YouTube and it’s use in the recommender system
Some recommender systems rely on explicit feedback like user ratings or likes and dislikes. YouTube recently decided to not show the count of dislikes on...
China seeks feedback on a draft for regulating online recommendations
According to Stanford’s DigiChina Cyber Policy Center, China seeks feedback on a draft for a policy that would regulate companies that use recommender systems. More...
Should Recommender Systems Be Exempt From the Post-Tracking Age? [Martin Anderson@Unite.ai
As first-party data gathering becomes the new lodestar for marketers and data brokers, the increased attention on ‘closed’ data-gathering systems risks to drag one of machine...
YouTube’s recommendations are still bad – says Mozilla
New research published today by Mozilla backs that notion up, suggesting YouTube’s AI continues to puff up piles of “bottom-feeding”/low-grade/divisive/disinforming content — stuff that tries...
Experience of using CORE Recommender – an interview
The CORE recommender is recommender-system-as-a-service and API for research-paper recommendations (similar to my own service Mr. DLib). CORE has an impressive open source repository of...
Google AI releases ‘RecSim NG’, a “Flexible, Scalable, Differentiable Simulation of Recommender Systems”
One or two years ago, Google AI released RecSim — A Configurable Simulation Platform for Recommender Systems. Now, Martin Mladenov from Google AI announced the...
Google Chrome’s Update on Privacy Sandbox Initiative (Browser Tracking without 3rd-Party Cookies)
Third-party cookies are were a central component to personalized advertisement on the Web. Due to GDPR, privacy concerns of users, and other reasons, using third-party...
Facebook Quietly Suspended Political Group Recommendations Ahead Of The US Presidential Election [BuzzFeed]
A few days before the US election, Facebook deactivated its recommender system for political content, according to BuzzFeed (Ryan Mac & Craig Silverman). Interestingly, this...
Big tech’s ‘blackbox’ [recommendation] algorithms face regulatory oversight under EU plans [Natasha Lomas @ TechCrunch]
The EU plans to require large tech firms to disclose how their algorithms work, including recommendations algorithms, reports Natasha Lomas from TechCrunch. In a speech today Commission...
‘Papers with Code’ partners with arXiv to increase reproducibility
This is exciting news, not only for the recommender-system community but many more: Robert Stojnic announced that Papers with Code partners with arXiv. Pre-Prints on...