Skip to Content
Policy

Pairing AI with Humans Has Made Glassdoor a Success Story in the War on Trolls

January 16, 2018

Glassdoor, the jobs search and ratings site, has been able to build a collaborative working environment for its human and AI content reviewers.

The AI’s job: Machine-learning algorithms scan for fraud and profanity on the site. Cara Barry, who leads the Glassdoor fraud team, told the New Yorker that their software searches for, among other things, people leaving multiple five- or one-star reviews to improperly affect a company’s ranking. It can also use text analysis to find inappropriate posts.

The human job: Human moderators review posts that machines and Glassdoor users have flagged. They look for things ranging from critique of employees below the C-suite (which is not allowed on the platform) to racist comments about coworkers.

The partnership: While glaring holes exist in the AIs that review content for companies like Youtube and Facebook, Glassdoor has been able to use the technology with great success. Instead of manually reviewing all posts as Glassdoor employees have done in the past, humans now have to look at only about half of them, significantly lightening their load while keeping would-be trolls at bay.

Deep Dive

Policy

Is there anything more fascinating than a hidden world?

Some hidden worlds--whether in space, deep in the ocean, or in the form of waves or microbes--remain stubbornly unseen. Here's how technology is being used to reveal them.

Africa’s push to regulate AI starts now        

AI is expanding across the continent and new policies are taking shape. But poor digital infrastructure and regulatory bottlenecks could slow adoption.

Yes, remote learning can work for preschoolers

The largest-ever humanitarian intervention in early childhood education shows that remote learning can produce results comparable to a year of in-person teaching.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.