Google recently published a report revealing how it catches fake business reviews and profile accounts. The company updated its machine learning systems to remove more fake reviews, fraudulent contributed images and videos, and fake business listings. Google’s automated systems and human review teams removed over 200 million photos, 7 million videos, and blocked or removed over 115 million reviews, representing a 20% increase over the prior year.
Google uses new machine learning models to catch and remove fake and fraudulent content, which includes flagging new forms of abuse that had not previously been seen. Last year, Google launched a significant update to its machine learning models that helped identify novel abuse trends faster than in previous years. For example, Google’s automated systems detected an uptick in Business Profiles with websites ending in .design or .top, which would have been difficult to spot manually.
Google’s systems review new content before it is posted 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. Google deployed a new machine learning model that could recognize numbers overlaid on contributed images by analyzing specific visual details and the layouts of photos. In 2022, Google will continue to improve its systems to catch and remove fake content.
Overall, Google is committed to ensuring that its users have access to accurate and trustworthy information. The company’s automated systems and human review teams work together to identify and remove fraudulent content, including fake reviews, fake business listings, and fraudulent contributed images and videos. Google will continue to improve its systems to catch and remove fake content in the future.