Today, we are taking another major step in our ongoing efforts to increase transparency.
We’re open-sourcing the code that affects a post’s visibility in the For You timeline, and releasing a new tool that shows people labels applied to their account or posts that might limit visibility.
The goal is straightforward – we want people to be able to answer for themselves whether a platform is limiting their reach, whether the system is fair, and why they see particular content.
The code and the label transparency tool are designed as two puzzle pieces that neatly fit together. The code shows you how the For You timeline is generated, including which labels impact visibility and their effect – the tool shows you whether your posts or account have those labels.
How it works:
- We’re releasing the code that determines how posts are ranked and filtered in the For You timeline, including the content labels that can impact post visibility. This builds on our previous open-source work, adding model configuration, filter and core ranking system details.
- We’re pairing it with post-level and account-level label transparency. This will allow people to see whether their posts or account have visibility-limiting labels.
- People will be able to check for themselves via a new ‘Under the Hood’ page – if you’ve posted 10+ times in the prior month, you’ll be able to see the labels applied to your account and posts in that month, and download the data. We’re rolling this out as a pilot, and plan to shape and expand its availability based on feedback from the public. Initially it will be available to a randomized test group of eligible accounts that are at least one year old.
- We’ve designed the system to facilitate ongoing updates as the algorithm evolves, and we look forward to making these regularly.
We have invited third-party recommender system experts to preview and pressure-test this code release in advance so it’s as clear and useful as possible to the public.
We hope you’ll find it helpful, too, and we appreciate your feedback and requests.
Follow the work here: https://github.com/xai-org/x-algorithm.
We are committed to setting a new standard for transparency – and we invite the rest of the industry to join us.
