E-commerce giant Amazon is using artificial intelligence (AI) to combat the explosion of fake reviews on its website. These efforts have resulted in the removal of over 200 million suspected fake reviews from its platform in 2022 alone.
Amazon uses AI to look at a bunch of special information to figure out if a review is real or fake. These machine learning models check things like whether the seller paid for ads, if customers complained about something fishy, strange patterns in behaviour, and the history of reviews. Amazon also uses large language models to find weird things in the data that could show a review is fake, like if someone got a free gift card or product for leaving a review.
“Fake reviews intentionally mislead customers by providing information that is not impartial, authentic, or intended for that product or service,” said Josh Meek, senior data science manager on Amazon’s Fraud Abuse and Prevention team. “Not only do millions of customers count on the authenticity of reviews on Amazon for purchase decisions, but millions of brands and businesses count on us to accurately identify fake reviews and stop them from ever reaching their customers. We work hard to responsibly monitor and enforce our policies to ensure reviews reflect the views of real customers, and protect honest sellers who rely on us to get it right.”
Amazon uses deep graph neural networks to analyze and understand complex relationships and behavior patterns to help detect and remove groups of bad actors or point towards suspicious activity for investigation.
“The difference between an authentic and fake review is not always clear for someone outside of Amazon to spot,” Meek said. “For example, a product might accumulate reviews quickly because a seller invested in advertising or is offering a great product at the right price. Or a customer may think a review is fake because it includes poor grammar.”
The combination of advanced technology and proprietary data helps Amazon identify fake reviews more accurately by going beyond the surface level indicators of abuse to identify deeper relationships between bad actors.
“Maintaining a trustworthy shopping experience is our top priority,” said Rebecca Mond, head of external relations, Trustworthy Reviews at Amazon. “We continue to invent new ways to improve and stop fake reviews from entering Amazon and protect our customers so they can shop with confidence.”