We use unique software to detect fake reviews and maintain the trustworthiness of our online review community.
No system is perfect, but computers tend to be more accurate than the average person at spotting fake reviews.* That's why we combine customized software with an international team of dedicated analysts, investigators and agents who work with reviews every day.
How does our software work?
In order to detect and remove fake reviews, we have a technical team dedicated to building and refining unique fraud detection software. And we’re always working to improve it. We can’t reveal exactly how our software works because that would defeat its purpose. What we can tell you is that it runs independently, 24/7 across our platform, examining a large range of different behavioral parameters - such as, for example, IP addresses. The system then uses an algorithm to calculate the likelihood that reviews are fake. This is represented by a ‘fake score’.
When are reviews removed by our software?
If the score for an individual review is very high, our software will automatically move the review offline and send an email message to notify the reviewer. At this stage, none of our employees are directly involved - everything is handled by the software alone.
As a starting point, all reviews are treated equally by our software. It doesn’t factor in or have access to information about whether a company subscribes to Trustpilot’s services or not. In line with our commitment to trustworthiness, we believe that’s how it should be.
What can reviewers do if they think there's a mistake?
Our system tends to be extremely accurate, but reviewers can contact us if they think there's been a misunderstanding. This happens rarely, but because we move reviews offline rather than delete any that are deemed fake by our system, we can always reinstate them at a later date.
Reviewers should also check that their review complies with our guidelines. Contravention of our rules can also result in a review being removed.
Why use software to assess reviews?
Usually, untrained readers of reviews focus on the language, rhythm and tone of the writing - linguistic indicators - to determine trustworthiness. And this tends to be relatively inaccurate because good writers can copy expressions used in genuine reviews in order to deceive readers.** In contrast, our software looks at behavioral aspects based on raw data, which tends to be more accurate.
In any event, it’s always necessary to look at a full range of indicators. We never remove a review based on one parameter alone - it’s always multiple factors that lead to taking something offline.
Manual processes support our software
On top of Trustpilot’s fully automated software, our specially trained Content Integrity Agents and Investigators also have access to powerful tools that help them manually examine review patterns for anomalies. These systems highlight any unusual and persisting patterns using a range of data.
Our team can use these factors to investigate and decide whether exceptional patterns indicate problems or have a logical explanation. This combines the best of both worlds - technology flags patterns that the human eye may not see, and our Content Integrity Team can use these elements to investigate further.
We take seriously our responsibility to uphold the credibility of reviews and always investigate cases that are brought to our attention as suspicious. Read more about our Whistleblower function here.
*See: http://www.news.cornell.edu/stories/2011/07/cornell-computers-spot-opinion-spam-online-reviews. **Mukherjee, A.; Venkataraman, V.; Liu, B.; Glance, N. What Yelp Fake Review Filter Might Be Doing? International AAAI Conference on Web and Social Media, North America, jun. 2013. Available at: http://www.aaai.org/ocs/index.php/ICWSM/ICWSM13/paper/view/6006. Accessed: 27 August 2019.