The ultimate guide to the facebook edgerank algorithm


Yesterday at its f8 developer conference, Facebook engineers Rubỏ ra Sanghvi & Ari Steinberg gave sầu what may be the first thorough walkthrough of the underpinnings of Facebook News Feed, the all-important page that users see when they first log on lớn the site. After giving an overview of the history of News Feed, which has evolved quite a bit since it launched in 2006, they offered some insight into lớn the algorithms that allow News Feed lớn show you relevant nội dung, collectively called EdgeRank.

Bạn đang xem: The ultimate guide to the facebook edgerank algorithm

You may not realize it, but News Feed only displays a subset of the stories generated by your friends — if it displayed everything, there’s a good chance you’d be overwhelmed. Developers are always trying khổng lồ make sure their sites & apps are publishing stories that make the cut, which has led khổng lồ the concept of “News Feed Optimization”, & their success is dictated by EdgeRank.

At a high màn chơi, the EdgeRank formula is fairly straightforward. But first, some definitions: every cống phẩm that shows up in your News Feed is considered an Object. If you have an Object in the News Feed (say, a status update), whenever another user interacts with that Object they’re creating what Facebook calls an Edge, which includes actions lượt thích tags và comments.


Each Edge has three components important to Facebook’s algorithm:

First, there’s an affinity score between the viewing user and the item’s creator — if you skết thúc your frikết thúc a lot of Facebook messages và check their profile often, then you’ll have sầu a higher affinity score for that user than you would, say, an old acquaintance you haven’t spoken khổng lồ in years.Second, there’s a weight given khổng lồ each type of Edge. A comment probably has more importance than a Like, for example. And finally there’s the most obvious factor — time. The older an Edge is, the less important it becomes.

Multiply these factors for each Edge then add the Edge scores up & you have an Object’s EdgeRank. And the higher that is, the more likely your Object is to lớn appear in the user’s feed. It’s worth pointing out that the act of creating an Object is also considered an Edge, which is what allows Objects to show up in your friends’ feeds before anyone has interacted with them.

Xem thêm: Hướng Dẫn Cách Đổi Tên Facebook Có Chữ Anh ? Cách Đổi Tên Facebook Có Chữ Anh

In other, hopefully less confusing words, an Object is more likely lớn show up in your News Feed if people you know have sầu been interacting with it recently. That really isn’t particularly surprising. Neither is the resulting message to developers: if you want your posts to show up in News Feed, make sure people will actually want lớn interact with them.

Some other interesting points: Steinberg hinted that a simpler version of News Feed may be on the way, as the current two-tabbed system is a bit complicated. That said, many people still use both tabs, with over 50% of users clicking over lớn the ‘most recent’ tab on a regular basis.

There were some things that the Facebook engineers wouldn’t talk about — the group sort of punted on a question regarding how stories initially get seeded, explaining that they weren’t going to lớn unveil all of EdgeRank’s secrets. But they did say that there are some signals involved that weren’t detailed during the talk, và that they’re experimenting with more, like analyzing the outbound liên kết users cliông chồng on.

If you want to lớn watch the đoạn phim for yourself, click here, navigate khổng lồ the Techniques sessions, và click on ‘Focus on Feed’. The talk about Facebook’s algorithms begins around 22 minutes in.