Sunday, 1 January 2017

How does your Facebook algorithm work?

          Many of us might be wondering how Facebook works and why you see only particular posts posted by friends or the fan pages you follow. Here are the answers. The algorithm that Facebook uses to manage newsfeed is edgerank algorithm.
What is that Edgerank algorithm and why?
ü Usually we won’t be able to see all posts posted by our friends or the fan pages we follow. Facebook decides what posts to be shown in each users newsfeed.

ü This algorithm helps in hiding the boring stories. EdgeRank is like a rating point: it's invisible, it's important, it's unique to each user, and no one other than Facebook knows exactly how it works.  Facebook calls every action we perform as "Edges."

ü  That means whenever a friend posts a status update, comments on another status update, tags a photo, joins a fan page it generates an "Edge," and a story about that Edge might show up in the user's personal newsfeed.
The formula is
                       ∑ ue we de
    
                                 Ue  - affinity score
                                 We - weight for each edge
                  De - time decay factor

Affinity score
ü  The affinity score generally deals with how people are connected a particular person. More specifically speaking Facebook calculates affinity score by looking at explicit actions that users take, and factoring in


1) The strength of the action

2) How close the person who took the action was to you

3) How long ago they took the action.

ü  The actions include clicking, liking, commenting, tagging, sharing, and friending. Each of these interactions has a different weight that reflects the effort required for the action more effort from the user demonstrates more interest in the content.

ü   The affinity score doesn't include your actions alone it includes your friends actions too.  


 Edge weight
ü  In Facebook each category of edges(actions) have different weights. 

ü  Facebook changes the edge weights to reflect which type of stories they think user will find most engaging. For example, photos and videos have a higher weight than links. Simply speaking comments will add more weights that like does.

ü   New Facebook features generally have a high Edge weight in order to promote the feature to users. For example, when Facebook checks Places rolled out, check-ins had a very high default weight for a few months and your newsfeed was probably inundated with stories like "Shyam checked into Dominos". Generally, after a few weeks or months Facebook dials the new feature back to a more reasonable weight.


Time decay
ü The time decay is another important part in Edgerank algorithm. 

ü For instance I’m updating my status today and after two days the status gets old and gradually it loses score.

ü The Edgerank score is changes every time, it’s not fixed score. Your status update will only hit the newsfeed if it has a higher score--at that moment in time--than the other possible newsfeed stories. 

ü Mostly the time decay factor is based on how long and how frequently the user uses the Facebook.


Prediction and other information
ü Practically speaking it’s not possible to check your score using Edgerank algorithm. But you can measure the effects of EdgeRank by seeing how many people you reached.

ü Moreover Facebook keeps the algorithm a secret, and they're constantly tweaking it. So the value of comments compared to likes is constantly changing.

ü Apart from that, best time for your posting your updates are 7am, 5pm and 11pm. Why those are considered best and others not? Many private organizations conducted many surveys on reaching their people.

ü Everyday morning before the leaving out for work(5am), evening after returning from work(5pm) and night before going to sleep(11pm) are more chances for checking on newsfeed. So when you post your updates on those times there are more chances of reaching more audiences. 

1 comment:

  1. Hi! Edgerank is now just a very small part of the Facebook newsfeed algorithm. Here is an interesting point : http://wallaroomedia.com/facebook-newsfeed-algorithm-change-history/

    ReplyDelete