Google published a blog post that shared that they updated their machine learning systems in order to catch and remove more fake reviews, fake business listings and fraudulent contributed images and videos.

The automated systems and human review teams removed over 200 million photos, 7 million videos and blocked or removed over 115 million reviews, which represents a 20% increase over the prior year, 2021.

How Google Catches User Contributed Spam

Google is using brand new machine learning models to catch and remove fake and fraudulent content.

These machine learning models look for unusual patterns in user contributed content, including flagging new forms of abuse that hadn’t previously been seen.

Google shared:

“We’ve long used machine intelligence to help us spot patterns of potential abuse, and we continue to evolve our technology.

Last year, we launched a significant update to our machine learning models that helped us identify novel abuse trends many times faster than in previous years.

For example, our automated systems detected a sudden uptick in Business Profiles with websites that ended in .design or .top — something that would be difficult to spot manually across millions of profiles.

Our team of analysts quickly confirmed that these websites were fake — and we were able to remove them and disable the associated accounts quickly.”

Google’s systems review new content before it is posted in order to block fake or fraudulent content submitted to the Google Maps system.

They also deploy a machine learning model to scan content that is already published, to catch fake content that may have slipped through the initial reviews.

These new systems block spam faster than in 2021 and catch more of it.

Google explained:

“In some places, scammers started overlaying inaccurate phone numbers on top of contributed photos, hoping to trick unsuspecting victims into calling the fraudster instead of the actual business.

To combat this issue, we deployed a new machine learning model that could recognize numbers overlaid on contributed images by analyzing specific visual details and the layouts of photos.

With this model, we successfully detected and blocked the vast majority of these fraudulent and policy-violating images before they were published.”

Spam Blocking Statistics

Google’s announcement shared that in 2022:

• Google blocked or removed over 115 million reviews, saying that the majority were blocked before being published.
• The new spam fighting algorithms removed over 200 million photos and more than 7 million videos that violated Google’s content policies.
• Blocked 20 million attempts to create fake business profiles.
• Added heightened protection for over 185,000 businesses that were experiencing suspicious activities.

In January 2023, Google sent a comment to the FTC (read the PDF here) that shared that Google uses signals to identify fake accounts, in addition to reviewing the content.

Google also shared that it now scanning images to detect content overlayed on the images that is meant to divert phone calls away from a business and toward the scammers phone number.

They check for bots, duplicate content, word patterns that are similar to known fake reviews, and also use a system they call “intelligent text matching” that helps identify misleading content.

Authentic, Safe and Reliable

Google uses both automated and human reviewers in their efforts to block inauthentic activity on the Google Maps ecosystem.

Catching fraudulent activities on Google Maps is important for both the people who depend on the business reviews and the businesses who have businesses listed in the system.

Featured image by Shutterstock/ViDI Studio

Source: Google