Could Snap save the internet from fake news? Here’s the company’s secret weapon

snapchat supporting algorithm fight fake news vagelis papalexakis
Vagelis Papalexakis UC Riverside

When Snapchat was first pitched as part of a Stanford mechanical engineering class, the course’s horrified teaching assistant openly wondered if the app’s creators had built a sexting app. Less than a decade later, Snapchat could help solve one of the biggest problems currently facing tech: stopping the spread of “fake news” online.

With this goal in mind, Snap Research — the research division of Snap, Inc. — recently donated funding to a University of California, Riverside project, aiming to find a new way of detecting fake news stories online. The algorithm UC Riverside has developed is reportedly capable of detecting fake news stories with an impressive accuracy level of up to 75 percent. With Snap’s support, they hope to further improve this.

“As I understand it, they’re very interested in having a good grasp on how one could understand this problem — and solve it ultimately.”

“Snap is not one of the first companies that would come to mind given [this problem],” Vagelis Papalexakis, Assistant Professor in the Computer Science & Engineering Department at UC Riverside, told Digital Trends. “Nevertheless, Snap is a company which handles content. As I understand it, they’re very interested in having a good grasp on how one could understand this problem — and solve it ultimately.”

What makes UC Riverside’s research different to the dozens, maybe even hundreds, of other research projects trying to break the fake news cycle is the ambition of the project. It’s not a simple keyword blocker, nor does it aim to put a blanket ban on certain URLS. Nor, perhaps most interestingly, is it particularly interested in the facts contained in stories. This makes it distinct from fact-checking websites like Snopes, which rely on human input and evaluation instead of true automation.

“I do not really trust human annotations,” Papalexakis said. “Not because I don’t trust humans, but become this is an inherently hard problem to get a definitive answer for. Our motivation for this comes from asking how much we can do by looking at the data alone, and whether we can use as little human annotation as possible — if any at all.”

The signal for fake news?

The new algorithm looks at as many “signals” as possible from a news story, and uses this to try and classify the article’s trustworthiness. Papalexakis said: “Who shared the article? What hashtags did they use? Who wrote it? Which news organization is it from? What does the webpage look like? We’re trying to figure out which factors [matter] and how much influence they have.”

For example, the hashtag #LockHerUp may not necessarily confirm an article is fake news by itself. However, if a person adds this suffix when they share an article on Twitter, it could suggest a certain slant to the story. Add enough of these clues together, and the idea is that the separate pieces add up to a revealing whole. To put it another way, if it walks like a duck and quacks like a duck, chances are that it’s a duck. Or, in this case, a waddling, quacking, alt-right Russian duck bot.

“Our interest is to understand what happens early on, and how we can flag something at the early stages before it starts ‘infecting’ the network,” Papalexakis continued. “That’s our interest for now: working out what we can squeeze out of the contents and the context of a particular article.”

The algorithm developed by Papalexakis’ group uses something called tensor decomposition to analyze the various streams of information about a news article. Tensors are multi-dimensional cubes, useful for modeling and analyzing data which have lots of different components. Tensor decomposition makes it possible to discover patterns in data by breaking a tensor into elementary pieces of information, representing a particular pattern or topic.

“Even a ridiculously small number of annotated articles can lead us to really, really high levels of accuracy”

The algorithm first uses tensor decomposition to represent data in such a way that it groups possible fake news stories together. A second tier of the algorithm then connects articles which are considered to be close together. Mapping the connection between these articles relies on a principle called “guilt by association,” suggesting that connections between two articles means they are more likely to be similar to one another.

After this, machine learning is applied to the graphs. This “semi-supervised” approach uses a small number of articles which have been categorized by users, and then applies this knowledge to a much larger data set. While this still involves humans at some level, it involves less human annotation than most alternate methods of classifying potential fake news. The 75 percent accuracy level touted by the researchers is based on correctly filtering two public datasets and an additional collection of 63,000 news articles.

“Even a ridiculously small number of annotated articles can lead us to really, really high levels of accuracy,” Papalexakis said. “Much higher than having a system where we tried to capture individual features, like linguistics, or other things people may view as misinformative.”

A cat-and-mouse game for the ages

From a computer science perspective, it’s easy to see why this work would appeal to Vagelis Papalexakis and the other researchers at UC Riverside — as well as the folks at Snapchat. Being able to not only sort fake news from real news, but also distinguish biased op-eds from serious journalism or satirical articles from The Onion is the kind of big data conundrum engineers dream of.

The bigger question, however, is how this algorithm will be used — and whether it can ultimately help crack down on the phenomenon of fake news.

Snap’s contribution to the project (which amounts to a $7,000 “gift” and additional non-financial support) does not guarantee that the company will adopt the technology in a commercial product. But Papalexakis said he hopes the research will eventually “lead to some tech transfer to the platform.”

app attack google news 8

The eventual goal, he explained, is to develop a system that’s capable of providing any article with what amounts to a trustworthiness score. In theory, such a score could be used to filter out fake news before it even has the chance to be glimpsed by the user.

This is a not dissimilar idea to machine learning email spam filters, which also apply a scoring system based on factors like the ratio of image to text in the body of a message. However, Papalexakis suggested that a preferable approach might be simply alerting users to those stories which score high in the possible fake category — “and then let the user decide what to do with it.”

One good reason for this is the fact that news does not always divide so neatly into spam vs. ham categories, as email does. Sure, some articles may be out-and-out fabrication, but others may be more questionable: featuring no direct lies, but nonetheless intended to lead the reader in one certain direction. Removing these articles, even when we might find opinions clashing with our own, gets into stickier territory.

“This falls into a gray area,” Papalexakis continued. “It’s fine if we can categorize this as a heavily biased article. There are different categories for what we might call misinformation. [A heavily biased article] might not be as bad as a straight-up false article, but it’s still selling a particular viewpoint to the reader. It’s more nuanced than fake vs. not fake.”

Ultimately, despite Papalexakis’ desire to come up with a system that uses as little oversight as possible, he acknowledges that this is a challenge which will have to include both humans and machines.

“I see it as a cat-and-mouse game from a technological point of view,” he said. “I do not think that saying ‘solving it’ is the right way to look at it. Providing people with a tool that can help them understand particular things about an article is part of the solution. This solution would be tools that can help you judge things for yourself, staying educated as an active citizen, understanding things, and reading between the lines. I don’t think that a solely technological solution can be applied to this problem because so much of it depends on people and how they see things.”

Emerging Tech

From electron microscopes to X-rays, high-tech tools expose low-tech art forgery

At the Indianapolis Museum of Art, conservation scientist Greg Smith and Glennis Rayermann, then a Ph.D student, used high-tech equipment to determine if a painting was made by master forger Icilio Federico Joni.

Galaxy S10 leak shows radical tech that could help Samsung kill the notch

While we still may be months away from an announcement, there's no doubt about it: Samsung is working hard on its successor to the Galaxy S9. Here's everything we know about the upcoming Samsung Galaxy S10.
Emerging Tech

A Fitbit for your cat shit: Automatic litter box tracks your kitty’s health

It may look like a sci-fi teleportation chamber, but Footloose is a high-tech litter box that promises to be the most cutting-edge way for your kitty to take a dump. Here's how it works.

A ThinkPad tablet with a foldable screen could be in Lenovo’s future

Lenovo may be working on its own version of Project Andromeda. The company is reportedly working on a 13-inch tablet that can fold down to just nine inches for travel by leveraging LG Display's foldable screen technology.

Huawei and Leica’s monochrome lens is dead, so we celebrate its life

The Huawei Mate 20 and Mate 20 Pro do not have a dedicated monochrome camera lens, unlike the P20 Pro, and various Huawei and Leica phones before it. It's the end of an era, and also the start of a new one, as Leica has worked on its…

NYPD pulls thousands of body cams after one explodes

The NYPD has recalled thousands of body cameras after one of them exploded during an officer's shift on Sunday, October 21. No one was injured in the incident, which is thought to have been caused by the device's battery.
Emerging Tech

There’s finally a way to trace ‘untraceable’ 3D printed guns

To help track 3D-printed guns, researchers have developed a new algorithm which is able to identify which 3D printer was used to print an object, based on its unique fingerprint. Here's how.
Emerging Tech

These solar-powered water purifiers can produce 30,000 gallons of water per day

Problems with contaminated water? Quench Water & Solar's water purifiers can purify up to 30,000 gallons of fresh water per day and it's offering the technology to whoever wants it.
Smart Home

Silo A.I. vacuum storage system tells you when your leftovers are going bad

"Alexa, is the chicken still OK to eat?" Newly launched on Kickstarter, Silo is a neat vacuum storage container that will extend your food's shelf life -- and add in a useful dose of A.I., too.
Emerging Tech

Watch the moment NASA releases 450,000 gallons of water onto a launch pad

NASA's next-generation rocket will be one of the most powerful ever made and at launch will generate a colossal amount of heat and noise. Here's what it's going to do to control all that energy ...
Emerging Tech

Elon Musk to give free rides in first Boring Company tunnel in December

Members of the public will soon get to find out if Elon Musk's high-speed tunnel plan is a serious effort at reducing traffic congestion or little more than a fancy theme park ride, with free rides being offered from December.
Emerging Tech

World’s first drone-equipped motorcycle features a special space for the Spark

If your sidecar is missing a drone or your drone a sidecar, then check out how the two machines have been brought together in this unique design from Ural Motorcycles. Only 40 have been made, though that may turn out to be enough.
Product Review

North’s Focals aim to keep you ‘heads-up’ with smartglasses

North, formerly known as Thalmic Labs, has unveiled a new product alongside the brand-name change. Focals is a pair of smartglasses, like Google Glass, that attempts to help keep you heads-up.
Emerging Tech

Meet the $1.5m Xprize winner that makes artificial clouds in shipping containers

Could the solution to a lack of clean drinking water be an artificial cloud inside a shipping container? It sounds crazy, but it just won the prestigious $1.5 million Water Abundance XPrize.