How AI Mitigates the Brand Damage of Five-Star Fakery

Niv Elad By Niv Elad | 10 Dec 2019

Better reviews equate to better perceptions and better sales. So, it should be no wonder that e-commerce vendors aim for the best possible reviews of their products. However, there are plenty of shady deals and dodgy online arrangements which inflate product reviews on platforms like Amazon.

It might not sound like much – but the difference between a three and a four-star rating can be crucial in converting browsers into buyers. Consider that an increase of just one star in a rating on Amazon correlates with a 26 percent increase in sales, according to a recent analysis by the e-commerce consulting firm Pattern.

That additional star helps sales but simultaneously confuses brand-customer relations. Customer experience is vital for online enterprises and fake reviews serve to obfuscate the actual feedback of actual customers. This is why Artificial Intelligence systems which understand how to flag reviews are gaining prominence and restoring communication between brand and buyer.

The Sway of the Online Review

Product reviews matter. Four out of five American adults check product reviews before making a purchase and research shows that consumers are more swayed by a simple star rating than what reviewers actually write. 

Consider this trend alongside the continued growth of online commerce revenue. US e-commerce grew to almost 15 percent of total retail sales to reach $517 billion in 2018.

It is in this context where fake reviews continue to boom. Some commentators estimate that almost 40 percent of Amazon reviews are fake and some websites like this one even sell Amazon reviews at $15 each. Brands want to inflate their star ratings and reap the commercial benefit. 

This is assisted by the fact that one of the biggest players, Amazon, hosts 1.8 million vendors and sellers with nearly 600 million items that generate about 9.6 million new product reviews every month. However, the system remains notoriously easy to fool. Evidently, reviews influence purchasing decisions but also remain unchecked by the vast majority of e-commerce platforms. That is until now.

Enter AI

Artificial Intelligence is bringing a, well, intelligent solution to finding the frauds. Self-learning artificial intelligence is learning to weed out the fakes, in bulk, by employing language processing methods to detect unusual patterns of text, writing style, and formatting.

For example, researchers at the University of Chicago in 2017 came up with a machine learning system, which was a deep neural network, and relied on the dataset of three million real restaurant reviews on Yelp.

Better yet – self-learning systems grow smarter with more fake reviews. Unlike human-trained AI, which relies on pre-defined keywords which can be fooled by the fake reviewers of the world, self-learning AI compares the reviews of each product to the industry’s standards and competitors. If it detects anomalies, it ignores the suspicious reviews in calculating sentiment analysis.

This is why machines which understand double sentiment based on a specific product and industry benchmarks are more accurate than human reviewers. The ‘human’ factor is responsible for about 90 percent of sentiment analysis errors – and eliminating this drastically improves false positive and false negative errors.

Restoring Buyer Trust

This should be to the delight – rather than apprehension – of the companies themselves. Fake reviews bring the entire customer feedback system into question and hurt the integrity of e-commerce platforms. Therefore, technology, which uncovers illegitimate reviews is a step in the right direction.

Fake reviews do more harm than good. Feedback which does not reflect actual customer experiences only confuses the relationship between brands and customers. Removing such fakes helps to better gauge customer relations and improve where needed.

Self-learning systems, for example, have been shown to better understand industry or product sentiment. Just like its ability to uncover fake feedback, machine learning and natural-language understanding processing can help analyse customer sentiment and customer feedback at scale. This tech easily filters millions of reviews and analyze the entire market on an ongoing basis, not only removing the fake reviews but presenting an unbiased depiction of market sentiment to any given brand at the same time.

In this way, AI allows consumer-centric enterprises to better grasp what customers feel towards their brand. For example, using this on social media is useful to engage in real-time social listening. Removing fake reviews from this equation serves to clarify what customers actually feel about a brand, and not what certain third-party influencers falsely generate.

The five-star fakes might pump up sales but do little to assist brands in the long-run. By using technology to automatically flag fraudulent feedback, only the genuine will remain – and it is only with genuine reviews by which companies can improve their respective service or product.

This article is by Niv Elad, VP Engineering of Revuze, the tech AI startup changing how organizations consume Customer Experience insights.

Like this story? Sign-up for the free Pulse Weekly Newsletter for more essential online retail content.

0 Comment

Leave a Reply

Your email address will not be published. Required fields are marked *

[gravityform id="11" title="false" description="false" ajax="true"]
  • This field is for validation purposes and should be left unchanged.