How do news feed algorithms work? Algorithms are an important piece of Internet marketing.
Lets use Facebook as an example but most work the same way. Facebook wants you to keep coming back. And to keep you engaged, they need to offer you interesting content to read. This content has to come largely from a p
ool of posts, photos, etc., created by your friends and pages you like. Let’s call them stories to simplify. The pools of stories you’re eligible to see are your candidate stories. Facebook has candidate selection principles around what’s considered a candidate, for example the story has to come from or be liked by someone in your friend or follow graph, and to maintain freshness there is a time window from which stories are considered.
When someone creates a post, a reference to that story is pushed to a candidate stream. When a friend logs in, newsfeed iterates over all their friends’ indexes to extract stories that might be interesting to them and then proceeds to rank them.
Ranking is the bread and butter of these products. In order to keep you engaged, one needs engaging stories, which are chiefly determined by signals such as your likelihood to click, like, comment or share them. These signals are also called actions, and they can be explicit (e.g. liking) or implicit (time spent on a page before returning to feed).
The core idea with newsfeeds is to use key words on past behavior to predict actionable probabilities in order to determine the most engaging stories and put them on top.
Are you beginning to see how this works? You are not seeing everything that is posted. Your only seeing what the particular platform thinks you want to see.
Algorithms will also show you pop up marketing Ads based on your searches and stories. There is a lot of money made via internet advertising from boosting posts and Ad’s (travel, wedding, etc.) and not just clicks. So companies are trying to find ways to optimize long-term metrics over short-term metrics. The problem with long-term metrics is that they’re too nebulous and sparse to perform effective machine learning. So, they approximate long-term engagement with short term leading indicators and can also encode this into the value function, for example by putting extra weight on stories rated well by manual raters.
It is also important to know that so many factors play into the algorithms. How many videos you post? How often do you post. Do you post on a regular schedule? You might be amazed how important consistency is not only to your readers and followers but also to your ranking on your social platforms.
