Connect with us


How Facebook Ranks News Feed Posts



Facebook published an article that explains how the Facebook News Feed algorithm works. Compared with Facebook’s news feed algorithm patent, both documents explain much about how Facebook ranks posts in the news feed.

Machine Learning and Ranking

Facebook’s news feed algorithm is a machine learning ranking system. It’s not just one algorithm though. It’s a combination of multiple algorithms that work together in different phases.

Parts of the algorithm do different things, like selecting “candidate” posts to show in a person’s news feed, eliminating posts with misinformation or clickbait, creating lists of friends that a person interacts with, topics that the person tends to engage with and then using all of these factors to rank (or not rank) posts in a Facebook news feed.

All of those different layers are applied in order to predict what a Facebook member is going to find relevant to them.

The goal of the algorithms is to to rank which posts show up in the news feed, the order they are in and to select the posts that a Facebook member is likely to be interested in and to interact with.

It’s not just a few signals either that are considered. Facebook states that they use thousands of signals.

According to Facebook:

“For each person on Facebook, there are thousands of signals that we need to evaluate to determine what that person might find most relevant… to predict what each of those people wants to see in their feed…”

Facebook News Feed Ranking Signals

Characteristics of a Facebook Post

One of the ranking signals that Facebook discusses is the “characteristics” of a post.

Facebook is using a feature or quality of a post and determining whether this is the kind of thing that a user tends to interact with more.

For example, if a post is accompanied with a colorful image and a member has a history of interacting with posts with colorful images, then that’s going to be ranked higher.

If a post is accompanied by a video and that’s what a Facebook member likes to interact with, then that’s going to be ranked higher for that member.

Whether the post has an image, a video, if friends of a user are tagged in the post, those and other characteristics of a post are used as a ranking factors for determining whether a post is going to be shown to a user and how high it’s going to be ranked in the news feed.

Facebook used the example of a fictional user called Juan (the name “John” in Spanish) to illustrate the characteristics ranking factor.

This is what Facebook said about the characteristics ranking factor:

“We can use the characteristics of a post, such as who is tagged in a photo and when it was posted, to predict whether Juan might like it.

For example, if Juan tends to interact with Saanvi’s posts (e.g., sharing or commenting) often and her running video is very recent, there is a high probability that Juan will like her post.

If Juan has engaged with more video content than photos in the past, the like prediction for Wei’s photo of his cocker spaniel might be fairly low.

In this case, our ranking algorithm would rank Saanvi’s running video higher than Wei’s dog photo because it predicts a higher probability that Juan would like it.”

Time is a Facebook Ranking Factor

Facebook’s example that was noted above also illustrate how time, in the form of how recently something was posted, can also be used as a ranking factor.

What’s interesting about the example of the fictional “Juan” is that Facebook mentioned that when a post was made is a ranking factor.

“We can use the characteristics of a post, such as who is tagged in a photo and when it was posted, to predict whether Juan might like it.”

That aspect of time as a ranking factor coincides with a relatively recent Facebook patent that states that how recently something was posted can be used as a ranking factor.

The Facebook news feed patent is called, Selection and Presentation of News Stories Identifying External Content to Social Networking System Users.

This is what the Facebook News Feed patent says:

“…news stories may be ranked based on chronological data associated with interactions with the news stories, so that the most recently shared news stories have a higher ranking.”

That seems to confirm the value in posting the same post more than once during the course of a day. It may reach different people across time periods and those who interact with the post may help it to be shown to their friends, etc.

Engagement and Interest

Another ranking factor involves predicting whether a user will be likely to be interested in or engage with a post. Facebook uses a number of signals to make that prediction.

The article is clear on that point:

“…the system determines which posts show up in your News Feed, and in what order, by predicting what you’re most likely to be interested in or engage with.”

And some of those factors that Facebook uses are signals from past posts and people that the user has interacted with. Facebook uses these past interactions to help it predict what a user will interact with in the future.

According to Facebook:

“These predictions are based on a variety of factors, including what and whom you’ve followed, liked, or engaged with recently.”

Facebook uses machine learning models to predict each of these different things. There’s a model that predicts what content a user will like, another model that predicts which post the user will comment on.

Each of these forms of engagement receive a ranking score and are subsequently ranked.

To summarize, the ranking process begins by identifying candidate posts to rank, from a pool of posts that were made since the user’s last login.

The next step is to assign ranking scores to each post.

This is how Facebook explains it by using an example of a fictional user named Juan:

“Next, the system needs to score each post for a variety of factors, such as the type of post, similarity to other items, and how much the post matches what Juan tends to interact with.

To calculate this for more than 1,000 posts, for each of the billions of users — all in real time — we run these models for all candidate stories in parallel on multiple machines, called predictors.”

Ranking Signals are Personalized to the User

An interesting insight into ranking factors is that they are weighted differently from one user to the next. Weighted means for when a ranking signal is more important than another ranking signal.

What Facebook revealed is that for one person, the prediction that they would “like” a post could have a stronger influence on whether that post is ranked.

For another user, the prediction that the user will comment on a post is given a stronger ranking weight.

Facebook shared:

“Next is the main scoring pass, where most of the personalization happens.

Here, a score for each story is calculated independently, and then all 500 posts are put in order by score.

For some, the score may be higher for likes than for commenting, as some people like to express themselves more through liking than commenting.

Any action a person rarely engages in (for instance, a like prediction that’s very close to zero) automatically gets a minimal role in ranking, as the predicted value is very low.”

What that means is that in order for a post to be successful, the post must inspire different forms of engagement from every user.

Contextual Features for Diversity of News Feed

The last step in the ranking process is to ensure diversity of the type of content that is shown in the news feed. That way the user’s feed doesn’t become repetitive.

Multiple Personalized Facebook Ranking Factors

Facebook didn’t list every ranking factor used to rank posts in a news feed. But they did give an idea, an overview of how the ranking process happens and what kinds of behavior are prioritized. We also learned that ranking signals are dynamic and can be weighted differently depending on the person.


How Does News Feed Predict What You Want to See?

How Machine Learning Powers Facebook’s News Feed Ranking Algorithm

Selection and Presentation of News Stories Identifying External Content to Social Networking System Users (PDF)

Sentiment Polarity for Users of a Social Networking System (PDF)

Re-Ranking Story Content (PDF)

Resolving Entities from Multiple Data Sources for Assistant Systems (PDF)


Community work for police employee who leaked confidential files that wound up on Facebook



Community work for police employee who leaked confidential files that wound up on Facebook

The National Intelligence Application holds a wealth of information about millions of New Zealanders. Photo / Peter McIntosh

A police employee who used intelligence software to pry into the lives of people her friend thought were suspicious has been sentenced to 80 hours community work.

Kayla Watson also took photos of four people’s secure police files and sent them to her friend, who then posted them in a Facebook chat group.

Early last year she was acting manager for the crime reporting line in Auckland when her friend contacted her about letterboxes being damaged and residents being harassed in her Massey neighbourhood.

“Dodge house was in our carpark attaching [sic] cars, breaking our letterboxes and fighting again last night,” she said to Watson over text.


Advertise with NZME.

According to the Crown summary of facts supplied to NZME, Watson responded with: “What’s the address, I’ll have a look?” She then logged into the police’s National Intelligence Application (NIA) and searched the address her friend had supplied.

The NIA is a secure police record system used to store information about millions of New Zealanders. It includes flags for firearms licence holders, people known by police to be HIV (Aids) positive, and alerts for paedophiles and convicted murderers.

Access requires a security clearance and its use is audited to ensure employees aren’t misusing it. When new employees are given access, they are warned they can only use it for work purposes and must have a reason for everything they search within the system.

Alerts within the system can be placed on addresses and occupants of that same address can be linked to it.


Advertise with NZME.

Watson clicked on four people associated with the address and then took photos on her phone of their files, which included the last three months of police callouts at the address.

“There is aaaalloooot [sic] against their address,” Watson said in a follow-up message to her friend. “Family violence, disorder, drug searches … the list goes on.”

She then sent the photographs she’d taken of the NIA files to her friend via Facebook messenger. Shortly after, the friend posted the images to a Facebook chat group containing 10 other people within the Massey area.

At least five of them had viewed it before police became aware. The photos were later removed from the group.

Watson’s lawyer, Todd Simmonds, told the court that he was seeking a discharge without conviction for his client and that the consequences for her employment with the police would be significant-enough as a punishment.

“Those consequences would be out of proportion to the overall gravity of what she foolishly did on the morning in question,” he told the court.

Simmonds said that it was likely Watson would be dismissed from the police if she was convicted and rejected the Crown’s submission that the offending had been premeditated.

Crown lawyer Rob MacDonald said that a key part of the offending was the harm Watson had caused to the community and the public’s trust and confidence in police and their ability to keep confidential information a secret.

He argued that there was an element of premeditation in her offending because it was several hours after her friend texted her that she logged onto NIA.

“It gave her several hours to contemplate her actions, it wasn’t knee-jerk offending reacting to events happening at that time,” he told the court this afternoon.


Advertise with NZME.

“This isn’t a street fight that happened in the heat of the moment.”

MacDonald said consequences for Watson were already under way and police would be awaiting the outcome of today’s hearing to see whether she had been convicted.

“This goes to the heart of the defendant’s role at the police and the access that sworn and non-sworn officers have to private information. It’s something the police audit themselves every year as they appreciate the consequences of unauthorised access,” MacDonald said.

Ultimately in the Manukau District Court this afternoon Judge Penelope Ginnen declined to grant Watson a discharge without conviction, but she didn’t agree with the Crown’s view that her offending had been premeditated.

“It is my view there was not a great deal of premeditation, it was a spontaneous decision and you acted on it with too little thought,” she said.


Advertise with NZME.

“Your position in the NZ Police requires a degree of trust to not misuse your position…you’ve breached that trust. You’ve worked for the police for a long time. You know that while things are monitored and audited the very nature of the work means it needs to be a high trust environment.”

Judge Ginnen said it was lucky that the information wasn’t shared further than the chat group.

“In this digital age it just takes a few clicks of a button for information to be distributed around the world.”

Judge Ginnen said Watson’s actions had damaged the police’s integrity, their trust within the community as well as the privacy of the individuals whose photos and files she shared.

“It was an appalling lapse of judgment on your part. But I do take into account that you didn’t do this for personal gain and you didn’t know your friend would share the information with the chat group,” she said.

“But it was a serious thing you did.”


Advertise with NZME.

In sentencing Watson to 80 hours community work Judge Ginnen said she took into account Watson’s early guilty plea, complete lack of criminal history and her otherwise exemplary record during eight years working for the police.

However, the aggravating factors around the breach of privacy and the privileged position Watson was in for having access to the information in NIA meant that she could not escape a conviction.

Watson was placed on restrictive duties after the discovery of the information breach and returned to work within a month.

The police told NZME in an emailed statement that they could not comment on Watson’s case as it was still an active employment investigation.

Since the NIA was introduced in 2001, there have been several instances of police misusing the system, including one sworn police officer who gave information to gangs. Another used it to access information about his Tinder matches.

According to data released to NZME under the Official Information Act, four breaches of the NIA have resulted in criminal charges in the past five years – two of which were uniformed staff and the others were civilians, with Watson being one of those people.


Advertise with NZME.

There are still 20 ongoing investigations into misuses of the NIA, with 13 of those involving sworn constabulary members.

Source link

Continue Reading


Facebook, Twitter, and Other Social Platforms Go Offline



Facebook, Twitter, and Other Social Platforms Go Offline

Everything is down. Wednesday afternoon, widespread outages began to affect many of the internet’s most popular services, both social networks and otherwise. As of this writing, Facebook, Instagram, Twitter, Pokemon Go, and the McDonald’s mobile application a just a handful of the many services suffering from log-in difficulties. According to DownDetector, there’s no regional basis for the services going offline and reports are coming in from all corners of the country.

Meta—the parent company of Facebook—is only reporting “Major disruptions” with its ad service while Twitter says all of its systems are operational. Despite the difficulties, all other status pages for the aforementioned services suggest everything is operational. Keep scrolling to see what people are saying.

Silver Linings


Source link

Continue Reading


Wannabe Blackpool councillor suspended by Tories after civil service staff called 'pedos' in Facebook post



Wannabe Blackpool councillor suspended by Tories after civil service staff called 'pedos' in Facebook post

A prospective Blackpool councillor has been suspended from the Conservative Party following a series of offensive posts on social media that called …

Source link

Continue Reading