More from Author Ben Oakley here: https://globelivemedia.com/author/ben-oakley/

Globe Live Media, Thursday, January 28, 2021

Facebook wants to reduce the visibility of political content on the social network, which is why you could make changes to the News Feed and stop the recommendations of groups focused on political and social issues.

The CEO and founder of Facebook, Mark Zuckerberg, shared this Wednesday during the presentation of the results corresponding to the fourth quarter and the balance of 2020, what are the company’s priorities for 2021.

Those priorities include limit the visibility of political content, for which they could modify the operation of the News Feed, although the manager has not specified how it would be done or if they will review what they consider to be policy, as highlighted in Globe Live Media.

In the framework of the US presidential elections, the platform stopped the suggestions of political and social groups, a measure that, according to Zuckerberg, could make permanent, and not only in that country.

“People do not want politics and struggle to take over their experience”, said the manager. He also assured that they were committed to freedom of expression, and that they did not want to limit users from sharing their political views. In this sense, he pointed out that the company would respond to comments that indicate that this content is “unpopular”.

How to predict what the user wants to see

Mark Zuckerberg, CEO of Facebook (Photo: EFE)

Mark Zuckerberg, CEO of Facebook.
 

The News Feed is the section of the Facebook social network where users can see new content of interest to you, displayed in a certain order driven by a ranking system of machine learning.

The rating system is a system used by Facebook to personalize content for more than 2 billion users around the world, so that what they see in the News Feed is “relevance and significant”.

For each user, the company explains on its official page, there are more than thousand potential publications. “We are talking about billions of publications for all the people who are on Facebook”, which joins the more than thousand signals that are evaluated from each user to determine what is most relevant for each one.

“So we have billions of posts and thousands of signals, and we need to predict what each of the people in their feed wants to see instantly.”, They point out from Facebook. The process that allows it works in the background and loads in “one second”.

The News Feed is the section of the Facebook social network where users can see new content of their interest, which is displayed in a specific order driven by a machine learning classification system (Photo: Reuters)

The News Feed is the section of the Facebook social network where users can see new content of their interest, which is displayed in a specific order driven by a machine learning classification system. 

The algorithm of Facebook is always spoken of as responsible for selecting the content that users will see. It is actually not a single algorithm but a multiple layers of machine learning models, as the company qualifies. And its function is simple: “Determine which posts appear in the News Feed and in what order, by predicting what the user is most likely to be interested in or engage in.

To do this, this system collects all candidate posts that can be ranked for a given person, including posts shared by a friend, a group or one page to which you are connected and that have been made since your last login and have not been deleted.

Each post is scored based on a number of factors, such as whether the person in question has indicated that a post is worth their time –for example, in some of the surveys that the social network actually takes-, the person who posted it and the extent to which the post matches what you usually see. Subsequently, a model reduces the pool of candidates to the most relevant publications, which are about 500.

Each of those 500 stories is scored independently and all of them are sorted according to their score. And finally, the contextual filter, in which contextual characteristics are added to ensure that each user’s News Feed has a good mix of content.

Categorized in: