Get all your news in one place.
100’s of premium titles.
One app.
Start reading
The Hindu
The Hindu
Lifestyle
Sowmya Ramasubramanian

How accurate are algorithms in detecting fake reviews online?

Photo for representation purpose (Source: Special Arrangement)

(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)

UK-based consumer watchdog Which said on Tuesday it exposed a web of paid reviewers who manipulate ratings of nearly 50 Google business listings. These listings ranged from home improvement companies, to stock brokers, and even a dental surgeon.

Fake online reviews continue to storm the internet, and most fraudsters are active on Google and Amazon. These reviewers are increasingly using sophisticated methods to stay ahead of each other by curating clever and invasive algorithms.

According to a 2019 survey by market research firm BrightLocal, nearly 80% people said they read a fake review, and a third of them said they spotted multiple fake reviews.

Also Read | Farming clicks to unethically boost followership on social media

While companies can now use algorithms to distinguish fake reviews from real ones, the extent to which websites use the algorithms is unclear and hence some fake reviews may slip through the net, according to a team of researchers at the University of York.

So, the team suggests users to trust their gut instincts when reading online reviews, instead of simply relying on computer algorithms.

For their study, the team asked 380 people about their perception on three hotels, based on reviews (some authentic and some fake). After analysing responses, the researchers concluded that online users often fail to detect fake reviews as they do not proactively look for deception cues.

Also Read | Mobile ad frauds rise as smartphone usage surges during the pandemic

The team noted that once users' default reading habit changes, they will be able to trust their gut instinct to spot fake reviews.

Users have the tendency to either approach online content with the assumption that it is all true or all fake, and neither of methods work in the online environment, according to Snehasish Banerjee, lecturer at University of York.

Sign up to read this article
Read news from 100’s of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.