Fighting fraud with fractions: New algorithm weeds out fake product reviews automatically

michelle bachmann fraudulent amazon product review

How often do you check the comments and number of stars a product has received prior to purchasing a service or product?

If you’re like most of us, the answer is nearly always. On the Web, positive or negative product reviews will often be the deal breaker — or maker — for potential customers. Which also makes faking them big business. To combat the growing market for fraudulent user reviews, researchers at the University of Illinois at Chicago with the backing of Google have developed an algorithm, dubbed GSRank, for weeding out fraudulent reviews.

Novice fraudulent reviews are easy to catch — reviewers will create a new account specifically to vilify or praise a single product. More complex operations use multiple accounts working in tandem to review multiple products. Yet this collaborative effort is what allows the algorithm to identify the fraudulent reviewers.

Looking at groups of reviews turns out to be the key. When a competitor intends to slander a rival, it’s likely that the fraudulent reviews will come from a group of multiple accounts, called “spammer groups.” The same grouping patterns appear in fraudulent “good” reviews meant to bolster the profile and desirability of a company’s own product.

Drilling down further, the researchers found eight signals for false reviews, which serve as the foundation for the algorithm that ultimately flags the fraudulent reviews. They are:

1. Group Time Window – A spam group will tend to publish its reviews within a short window of time.

2. Group Deviation – Reviews that deviate significantly from the others on a product may have a higher probability of being fake. 

3. Group Content Similarity – Whether you’d call it lazy or not, spammers will copy reviews from within their own spam group. After all, there isn’t much money to be made in a single review, and spending time on a single review is money that could have been made elsewhere.

4. Group Member Content Similarity – Like Group Content Similarity, a single reviewer may save time by reusing, with slight edits, a review for a similar product.

5. Group Early Time Frame – The earliest reviews will tend to have the biggest effect on swaying the decisions of potential customers. Accordingly, companies are inclined to hire spammers early in the product’s existence, so fraudulent reviews will typically be among the first to review the product or service.

6. Group Size Ratio – The size of a spam group with respect to the total number of reviewers will also be a sign of spammers.

7. Group Size – The larger the spam group’s size, the more damaging the reviews will be. The chances that the reviews will be submitted at the same time will also be slimmer. Larger spam groups are more inclined to intentionally time the review’s post, or if reviewers in spam groups have been selected individually, a post will be unlikely to be published at the same time.

8. Group Support Count – A group of potentially fraudulent accounts is far more likely to have reviewed the same products than a group of genuine accounts.

So far, the research, mining and manual detection of false reviews has been a laborious and expensive process. With the introduction of the researcher’s GSRank algorithm, the process can be mostly automated. Companies trying to work the system now have a formidable hurdle.

Emerging Tech

Awesome Tech You Can’t Buy Yet: Insect drones and kinetic sculpture robots

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it's fun to gawk!
Emerging Tech

Watch this drone dodge an incoming soccer ball autonomously

Most drones aren't very good at avoiding incoming objects. But now a team from the University of Zurich has developed a drone which can dodge, swoop, and dive to avoid an incoming football.
Emerging Tech

Experts warn 5G could interfere with weather forecasts, reducing accuracy by 30%

Experts and officials have warned that interference from 5G wireless radios could seriously compromise the ability to forecast weather, including the prediction of extreme weather events like hurricanes.
Emerging Tech

Chang’e 4 mission may have found minerals from beneath the surface of the moon

China's Chang'e 4 mission has made a major discovery: minerals that could be from beneath the surface of the moon. The lander spotted two unexpected mineral types which match what is believed to exist in the mantle.
Emerging Tech

See the impact site where the Beresheet spacecraft crashed into the moon

An image of the crash site of SpaceIL's ill-fated Beresheet spacecraft has been captured by NASA's Lunar Reconnaissance Orbiter and is being analyzed for information about the moon's soil.
Emerging Tech

See a fly-over of Mars and track the path Curiosity will take up Mount Sharp

A new animation from NASA shows a fly-over of Mount Sharp on Mars, the location where the Curiosity rover is currently exploring. It also shows the path that Curiosity will take over the next few years.
Emerging Tech

How Super Mario, Magic: The Gathering, and PowerPoint are low-key supercomputers

What if the creators of Super Mario World, PowerPoint, and even Magic: The Gathering had accidentally created tools hiding a general-purpose computer in plain sight? Turns out they have.
Emerging Tech

Two galaxies play tug of war in this spectacular Hubble image

Hubble has captured evidence of a nearby galactic neighbor affecting the the shape and star production of a galaxy. The irregular galaxy NGC 4485 has been pulled into an unusual shape due to the nearby and much larger galaxy NGC 4490.
Emerging Tech

The moon is shrinking as it loses heat, new images reveal

New research suggests the Moon is shrinking. NASA scientists have used data from their Lunar Reconnaissance Orbiter Camera to look at wrinkles in the surface of the Moon which are formed as it loses heat and shrinks in size.
Emerging Tech

Friendly cube robot Bumble passes its first hardware test aboard the ISS

There are some unexpected guests aboard the International Space Station (ISS): cute cube robots called Astrobees. Now the first Astrobee robot has undergone hardware tests to check whether its subsystems are working correctly.
Emerging Tech

Lilium Jet takes flight in first test for all-electric, five-seater aircraft

German startup Lilium had a successful maiden flight for its Lilium Jet. The all-electric, five-seater aircraft, powered by 36 engines fitted under its wings, looks to travel up to 300 kilometers in just 60 minutes.
Emerging Tech

Meatballs and pastries offered by Wing’s first European drone delivery service

Alphabet's Wing is getting ready to begin testing its drone delivery technology in Helsinki, Finland. At the start, customers will be able to order a variety of food and drinks, with delivery promised within about 10 minutes.
Emerging Tech

Impossible’s new plant-based sausage is here, but only at Little Caesar’s

Impossible Foods has teamed up with Little Caesars restaurants to create a new plant-based sausage pizza topping. Get ready for ... The Impossible Sausage. Here's where you can try it.
Emerging Tech

First, it was San Francisco. Now, the U.K. is fighting facial recognition

The U.K.'s first legal battle over police use of facial recognition has kicked off. The case involves a citizen who alleges the tech was used against him in a breach of his privacy.