Never miss a great news story!
Get instant notifications from Economic Times
AllowNot now


You can switch off notifications anytime using browser settings.

Portfolio

Loading...
Select Portfolio and Asset Combination for Display on Market Band
Select Portfolio
Select Asset Class
Show More
Download ET MARKETS APP

Get ET Markets in your own language

DOWNLOAD THE APP NOW

+91

CHOOSE LANGUAGE

ENG

  • ENG - English
  • HIN - हिन्दी
  • GUJ - ગુજરાતી
  • MAR - मराठी
  • BEN - বাংলা
  • KAN - ಕನ್ನಡ
  • ORI - ଓଡିଆ
  • TEL - తెలుగు
  • TAM - தமிழ்
Drag according to your convenience
ET NOW RADIO
ET NOW
TIMES NOW

Now, Flipkart's AI to help you find product reviews

, ET Bureau|
Updated: Oct 11, 2017, 09.12 AM IST
0Comments
Flipkart hopes to use all these insights to help its own customer experience team and also the brands, by giving them insights on what exactly matters to the customer.
Flipkart hopes to use all these insights to help its own customer experience team and also the brands, by giving them insights on what exactly matters to the customer.
BENGALURU: User review is a key element influencing online shoppers' buying decision in some categories such as mobile phones, televisions and air conditioners, and ecommerce giant Flipkart is experimenting with artificial intelligence (AI) techniques to help users find reviews that are relevant to them.

"Different users have different needs," said Ram Papatla, vice-president of product at Flipkart. "Popular categories like mobiles and electronics tend to attract thousands of reviews, making it impossible for users to consume all the information," he said.

Now, Flipkart gives people browsing through such products on the site a macro-level 'pie-chart' like view where they can see user ratings against key product aspects in the review section. It serves as a quick reference for the user to evaluate or compare multiple products.

Amar Nagaram, vice-president, engineering, at Flipkart, said, "Nouns become aspects, adjectives reflect the opinion."

He said every opinion has a polarity associated with it. "Say, awesome vs okay... Obviously, awesome is a higher positive sentiment."

On tapping on an aspect, the user is redirected to the reviews page where directed to the reviews page where he gets a more detailed view of the review snippets which contributed to the specific aspect rating.

This feature also has a set of challenges to deal with.

"What makes it difficult in the Indian context is there are a lot of grammatical errors. 'The camera is awsm', or, 'Camera accha nahi hai'. How do you interpret all these reviews?" Nagaram said.

Flipkart hopes to use all these insights to help its own customer experience team and also the brands, by giving them insights on what exactly matters to the customer. Rival Amazon has also been working on various experiments to make user reviews more understandable.
0Comments

Also Read

Flipkart sees the big picture in TV

Flipkart claims lead over Amazon in smartphones

Flipkart's small town push for Big Billion sale

Flipkart claims lead over Amazon in smartphones

Flipkart's small town push for Big Billion sale

Comments
Add Your Comments

Loading
Please wait...