The Maths of Facebook

Everyday millions of users will spend a quarter of their time on Facebook scrolling mindlessly through their Newsfeed. The Newsfeed, arguably the most important part of the site, is controlled by a unique algorithm called the ‘Edgerank’ algorithm. In this post, I’ll talk you through what this is and how it works.

What is it?

Edgerank is the algorithm that dictates what stories appear on a users Newsfeed. Say you are a Facebook user. Every action that your Facebook friends take is a possible Newsfeed story. Facebook calls these actions ‘edges’. Whenever someone visits their Newsfeed there are around 1,500 stories waiting to be seen, and since most people don’t have the time or simply don’t want to read through 1,500 posts, this algorithm prioritises the stories to show users what they’re most likely to be interested in. It is called ‘EdgeRank’ because it ranks the edges.

How does it work?

There are three things that this algorithm takes into consideration:

  1. Affinity Score
  2. Edge Weight
  3. Time Decay

Affinity Score

This means how ‘connected’ you are to the edge. It is calculated by considering how close you are with the person who’s posting. For example, if the story is by someone you frequently interact with, have several mutual friends with, or are related to, the algorithm is more likely to give the edge a higher affinity score.

Edge Weight

Not all actions, or edges, are considered to be of equal importance; a friend creating a status update would carry more weight than someone liking a photo.

Time Decay

As time passes and the posts gets older, it is likely that it has already been seen or that it is no longer as relevant. To solve this, the algorithm multiplies the story by 1/x, where x is the time since the action happened, to decrease its importance as time passes.

The formula below is then used to give each edge an overall score of importance:

the-three-pillars-of-edgerank-and-what-they-should-mean-to-you-equation.jpg

The higher the score, the more the story will be prioritised on your Newsfeed. Simple right!

Updates

Although the three factors remain the same, to refine the scores there are multiple weight levels and categories/sub-categories of affinity. Also, the algorithm now takes into account global interactions, which can outweigh personal interactions if the score is strong enough.

There are also relationship settings that Facebook users can apply; you can now label each of your Facebook friends a ‘close friend’ or ‘acquaintance’ (the stories of your ‘close friends’ will have a higher affinity score). Additionally, when you like a page you can now choose to ‘get notifications’ or ‘receive updates’ which is another way to control what appears on your Newsfeed.

Lastly, although the Edgerank algorithm is completely separate from the algorithm that decides what ads to show, when to show them and where, how you interact with these ads can influence what appears in your Newsfeed. Companies cleverly utilise this to get their advertisements to show up on their target audience’s Newsfeed.

Although this algorithm seems quite simple (in comparison to the PageRank algorithm) it is a vital component to the functionality of Facebook. Let me know what you think! M x

 

Advertisements

One comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s