Artificial Intelligence can spot fake online reviews

Sites like TripAdvisor, Yelp and Amazon display user reviews of products and services. Nine out of ten people read these peer reviews and trust what they see, researchers said.

Press Trust of India
Washington, Publish Date: Sep 18 2018 2:54PM | Updated Date: Sep 18 2018 2:54PM
Artificial Intelligence can spot fake online reviewsRepresentational Image

Scientists have developed an artificial intelligence (AI) system that can identify machine-generated fake reviews on online e-commerce websites.

Sites like TripAdvisor, Yelp and Amazon display user reviews of products and services. Nine out of ten people read these peer reviews and trust what they see, researchers said.

However, not all reviews are legitimate. Fake reviews written by real people are already common on review sites, but the amount of fakes generated by machines is likely to increase substantially.

According to doctoral student Mika Juuti at Aalto University in the US, fake reviews based on algorithms are nowadays easy, accurate and fast to generate.

Most of the time, people are unable to tell the difference between genuine and machine-generated fake reviews.

"Misbehaving companies can either try to boost their sales by creating a positive brand image artificially or by generating fake negative reviews about a competitor," said Juuti.

"The motivation is, of course, money: online reviews are a big business for travel destinations, hotels, service providers and consumer products," he said.

In 2017, researchers from the University of Chicago in the US described a method for training a machine learning model, a deep neural network, using a dataset of three million real restaurant ratings on Yelp.

After the training, the model generated fake restaurant reviews character by character.

There was a slight hiccup in the method, however; it had a hard time staying on topic. For a review of a Japanese restaurant in Las Vegas, the model could make references to an Italian restaurant in Baltimore. These kinds of errors are easily spotted by readers.

To help the review generator stay on the mark, Juuti and his team used a technique called neural machine translation to give the model a sense of context.

Using a text sequence of 'review rating, restaurant name, city, state, and food tags', they started to obtain believable results.

"In the user study we conducted, we showed participants real reviews written by humans and fake machine-generated reviews and asked them to identify the fakes," said Juuti.

"Up to 60 per cent of the fake reviews were mistakenly thought to be real," he said.

Researchers then devised a classifier that would be able to spot the fakes. The classifier turned out to perform well, particularly in cases where human evaluators had the most difficulties in telling whether a review is real or not.

Latest News

  1. India, Pakistan armies’ trade fire along LoC in Poonch
  2. India, Pakistan armies’ trade fire along LoC in Poonch
  1. JKLF chief Yasin Malik released on bail, re-arrested: Spokesperson
  2. JKLF chief Yasin Malik released on bail, re-arrested: Spokesperson
  1. PDP expels Basharat Bukhari, Peer Hussain from party
  2. PDP expels Basharat Bukhari, Peer Hussain from party
  1. Mumbai man, released from Pakistani prison, reaches India
  2. Mumbai man, released from Pakistani prison, reaches India
  1. Ending disbursement of subsidised sugar anti-people move: Farooq Abdullah
  2. Ending disbursement of subsidised sugar anti-people move: Farooq Abdullah
  1. Super-50 free coaching: DSEK declares waiting list of candidates
  2. Super-50 free coaching: DSEK declares waiting list of candidates
  1. Missing fitness trainer found hanging in north Kashmir’s Baramulla
  2. Missing fitness trainer found hanging in north Kashmir’s Baramulla
  1. Delhi HC seeks reply from Centre, jail on Asiya Andrabi's plea against solitary confinement
  2. Delhi HC seeks reply from Centre, jail on Asiya Andrabi's plea against solitary confinement
  1. Governor, his advisors must take responsibility of Pulwama civilian killings: Er Rasheed
  2. Governor, his advisors must take responsibility of Pulwama civilian killings: Er Rasheed
  1. Winter vacations announced for Jammu and Kashmir colleges
  2. Winter vacations announced for Jammu and Kashmir colleges
  1. On JRL call, funeral prayers in absentia held for Pulwama slain
  2. On JRL call, funeral prayers in absentia held for Pulwama slain
  1. Bihar school segregates students on caste lines, inquiry ordered
  2. Bihar school segregates students on caste lines, inquiry ordered
  1. PDP MP protests in Parliament against Pulwama civilian killings
  2. PDP MP protests in Parliament against Pulwama civilian killings
  1. Won't let PM sleep until all farms loans waived: Rahul Gandhi
  2. Won't let PM sleep until all farms loans waived: Rahul Gandhi
  1. Imran Khan hopes US-Taliban talks end Afghan suffering
  2. Imran Khan hopes US-Taliban talks end Afghan suffering
  1. Charred body of Kulgam resident found in Shopian
  2. Charred body of Kulgam resident found in Shopian
  1. Normalcy in Kashmir after three-day shutdown over Pulwama civilian killings
  2. Normalcy in Kashmir after three-day shutdown over Pulwama civilian killings
  1. Toll rises to 8 in Mumbai hospital blaze, 25 critical
  2. Toll rises to 8 in Mumbai hospital blaze, 25 critical
  1. Sajjan Kumar resigns from Congress primary membership, writes to Rahul
  2. Sajjan Kumar resigns from Congress primary membership, writes to Rahul
  1. Leopard mauls four-year-old to death in Jammu
  2. Leopard mauls four-year-old to death in Jammu
  1. Father of Hamid Ansari thanks India, Pakistan governments for son's release
  2. Father of Hamid Ansari thanks India, Pakistan governments for son's release
  1. No one can 'dictate' to China what it should, shouldn't do: Xi
  2. No one can 'dictate' to China what it should, shouldn't do: Xi
  1. Twitter warns 'unusual activity' from hackers in China, Saudi Arabia
  2. Twitter warns 'unusual activity' from hackers in China, Saudi Arabia
  1. Intense cold wave continues in Kashmir Valley, Ladakh
  2. Intense cold wave continues in Kashmir Valley, Ladakh
x
This site uses cookies to deliver our services and to show you relevant news and ads. By using our site, you acknowledge that you have read and understand our Cookie Policy, Privacy Policy, and our Terms of Service.That's Fine