How Amazon Is Using Artificial Intelligence to Crack Down on Fake Reviews

You can't always trust a five-star rating.

Using machine learning, Amazon's algorithm will bump up the reviews that are deemed to be the most true to customers' experiences, giving an extra weight to newer reviews and reviews that have been voted by customers as being helpful.

"Amazon is enhancing the customer reviews system, adding a few changes we hope will help make product feedback even more useful to customers," Julie Law, an Amazon spokeswoman, told ABC News in an email. "The system will continue to learn which reviews are most helpful to customers and improve the experience over time."

Amazon filed a lawsuit in April against several websites the company accused of selling positive reviews to help bolster a product's rating on Amazon. If Amazon's new system works to enhance user experience, it could deal a significant blow to such practices.

Product reviews have been a cornerstone of Amazon's business for the past two decades. The new machine learning algorithm is being rolled out first in the United States and it's expected the changes will at first be subtle. If successful, the algorithm could usher in a new era for trust and the online shopping experience.