Facebook News Feed Algorithm

Old Edgerank News feed alogrithm

Overview

Edgerank is old algorithm used by Facebook to rank the feed for user.

What is Edge?

An Edge is defined as any activity that occurs in Facebook and has a potential to make it into a newsfeed story. A classical example of edges are likes, posts, comments, tags, or RSVPs, however, this can really be any public activity that one of your friend undertakes.

Use of Edgerank algo

Edgerank decides whether this story (and edge it generates) makes it to your newsfeed or not, in addition to the potential position it will appear.

In other words, Facebook tries to evaluate the large amount of edges that are constantly created and pre-select those which it believes would interest you. This of course does not apply only to the edges created by users but also to edges that are created by Pages.

Edgerank factors

Edgerank algorithm consists of three main ingredients

1. Edge Affinity
2. Edge Weight
3. Time decay

Edge Affinity

1. Affinity score evaluates the relation you have with the edge creator.
2. The more interconnected you are, the higher the affinity score.
3. This interconnectedness is determined by the quantity and frequency which you engage with the creator and by the number of mutual connections.
4. It is also noteworthy that if you have a large number of Friends that like a similar Page, it is more likely that this content will arise in your
   newsfeed.

Edge Weight

1. Another factor influencing the formula is the “weight.”
2. There are two types of weights that are determined, the post weight and the the weight of an interaction.
3. Shares and comments require more from a user than a simple “Like” click, and therefore it is more heavily weighted.
4. Since users prefer visual communication such as photos (a pictures is worth a thousand words) and links, Facebook takes this into consideration and weights each post type differently.
5. We know that photos are almost always the most engaging type of content.

Time decay

1. An old story is a dead story.
2. Facebook does not chronologically order edges, however, it does factor in time to the algorithm.
3. Therefore, a fresh edge is more likely to appear in your newsfeed than an old one.

Edgerank as reach

We can not measure edgerank, but we can measure quite a few contributing factors are essential for understanding it.

What is Reach?

Whole point of Edgerank is to decide how many people the content will be displayed to, we can quantify this outcome as “Reach.”

Socialbakers

Of course, you have data about the reach of your own posts, but Socialbakers can make an educated guess at determining the reach
of brands by measuring aggregated engagement data.

Return on Engagement measurement

Since engagement directly correlates with reach, Return on Engagement (ROE) is something important to measure.

The Socialbakers’ Facebook Post ER formula is one Analytics PRO core metrics which determine the final percentage and show how well your brand is doing at engaging with your Fans.

Good practices for making your Edgerank soar!

1. QUALITY CONTENT
2. FOLLOW THE RULES
3. POST FORMAT
4. POST FREQUENCY
5. POST TIMING
6. RESPONDING FANS
7. KEEP AN OPEN HEAD

Machine learning based algorithm

Overview

Each feed is tailored to an individual to deliver content that has been predicted in order to provide the ideal platform for users. Facebook was the first platform to transit from a chronological wall to an algorithm based feed.

Machine learning approach that takes into account more than 10000 weights. It focuses on posts that are predicted to promote “active engagement”. This term denotes that the algorithm predicts scores by assigning greater weights to parameters that make a post personal and worthy of conversation.

The four parts of this algorithm are as follows:

Inventory

1. This comprises of all the posts in queue that are yet to be seen by the end user.
2. These posts include promotional content, posts from pages followed as well as content from friends.
3. Thousands of such posts must compete with one another each day to rise in the eyes of the algorithmic arbiter.
4. In the end, only a few hundred of these finally make it to the news feed of the user once the algorithm has made its decision, taking the parameters into consideration.

Signals

This stage is all about consideration about the content. Each post is analyzed based on the data available such as:

• Number of likes, comments, shares and reactions
• Type of post (video, images, written content)
• Owner of post
• Time and Day of post
• Speed of internet connection
• Type of device in use
• Blocked Content
• Marked as spam
• Time spent on post
• Top fifty interactions
• Video engagement (turning on audio, changing to full-screen or HD)

The signals above are generated from the users and given weightage. For example, sharing a post (personal/public) has greater weightage than liking or reacting to it. Similarly, content from family and friends are usually weighed higher than content from pages followed depending on the information gathered.

Predictions

1. The above-described data is then used to make informed decisions.
2. The algorithm attempts to make predictions based on information available to determine what the users prefer to see on their feed, what they may hide, how probable are they to engage with it actively or ignore it.
3. For example, a post from a friend who has previously received a comment from a user on a similar post in the past will likely be predicted to interest the user over content from a page followed that has received a like from the same user previously.
4. If video content is seen to be receiving higher engagement over written matter or images, such posts are predicted to be preferred by the user.

Scoring

1. These predicted posts in individual scenarios along with the weights are used to arrive at a relevancy score. The posts are then ordered based on this score in descending order. These posts are then delivered in the determined sequence to the news feed.
   The News Feed Algorithm is thus described as a “ranking to organize” approach.
2. Other news feed algorithms are also built on similar lines. However, the Facebook Algorithm is the most complex of all the News Feed Algorithms out there today. The mystery behind the detailed working of this complex algorithm is what withholds the ease of trust into the working of Facebook and researchers behind the scenes. Yet, it is continuously developing and surpassing the barriers of AI to provide a platform dedicated to connecting people.

Reference

https://www.geeksforgeeks.org/edgerank-algorithm-facebook-news-feed/#

https://www.geeksforgeeks.org/facebook-news-feed-algorithm/

https://assets.ctfassets.net/cpumif18y1gd/7wjoCzsrX7KpDIyX794t1Z/86461a0ac650d621792ae823cb70f0de/edgerank.pdf