How Facebook Reads Users’ Data and Desires – Facebook reveals how to guess what feed readers see, including using machine learning (ML) algorithms and predictors. This feature is claimed to support News Feed with many layers.
Reported by the official page, Facebook processes trillions of posts that are served to its more than 2 billion users. It sets up posts and thousands of signals to select posts that are relevant to its users.
It said that when a user opens Facebook, the selection process takes place behind the scenes in a matter of seconds to create a feed of posts that the user opens.
Once it is running then there are several layers of ML models and algorithms applied to predict meaningful and relevant content for each user.
As a user goes through several stages, the algorithm system narrows the thousands of candidate Feeds to a few hundred that appear in a person’s News Feed at any given time.
Simply put, a system that determines which posts appear in a user’s News Feed, and in the order in which the user is most interested. Reading this algorithm is based on several factors, including what and who the users follow, who they like and with whom the users interact.
For example, a user named Juan saw a photo of a friend’s rooster post and he saw another friend’s morning jog video post. But Juan reposted an article on how to see the Milky Way at night.
All of this content is considered relevant or interesting by Juan, so Facebook predicts the News Feed feed that has the highest value for Juan. In mathematical terms, Facebook defines an objective function for Juan and performs objective optimization.
Furthermore, Facebook also processes the characteristics of posts and photo posts tagged by its users. To rank more than a thousand user posts per day so that the process is efficient.
It manages the data in various steps, which are efficiently arranged to be fast to limit the amount of computing resources required.
Next, the system rates posts by various factors, such as how well a post fits a user to interact with other users.
In order to count more than 1000 posts and share them with billions of users at the same time, Facebook uses a system which is a parallel post reader engine called Predictor.
Predictor is an intelligent engine to combine and narrow interesting posts into approximately 500 posts.
Facebook runs contextual features such as a variety of content types that are of interest to users. All of these steps happen in a matter of seconds, and users have a scored News Feed ready to explore.
Source: https://www.cnnindonesia.com/technology/20220128143700-185-599542/cara-facebook-baca-data-tebak-keinginan-user
