Hike Is Using NLP-Based Stickers To Help Users Express Themselves In Indian Languages

Ankur Narang Hike

Popular messenger service Hike has been working on various innovations within the platform. Ever since it came into existence, the platform has acquired more than 100 million users and given the company enough impetus to keep improving their product. The company’s CEO Kavin Bharti Mittal earlier this year has announced an enhanced focus on the social and content front to create a unique experience among such apps using innovation. 

Hike has been working on sticker recommendations, message recommendations, vision, speech, anti-fraud, auto campaign tuning, and customer experience based optimisation using artificial intelligence. 

A significant chunk of that innovation falls in the lap of Dr Ankur Narang, VP of AI and Data Technologies, who recently spoke at India’s largest AI and analytics event, Cypher 2019. There, we had a chance to interact with him on the innovation at Hike concerning Natural Language Processing and AI. 

The company has been innovating to such heights that it joined the likes of IT giants like Wipro and TCS as the top patent filing organisations in India during the last few years. Hike may also look to integrate payments and other services to become India’s native super-app, as well as expand globally riding on its innovation and engineering stack.

“A few of our AI-driven innovations are in the areas of NLP, Deep Learning and computer vision. Apart from that, we are looking at more inward-facing problems in terms of reducing fraud and optimising the engineering stack. This is important as we are targeting different types of markets and looking at international expansions where innovation helps out a lot,” Narang said. 

One of the main features of Hike is its focus on Stickers on the messenger platform. The messenger has over 1 million stickers and if users wish they could interact using stickers on Hike Sticker Chat- a separate app altogether from Hike which recently crossed 1 million weekly actives. Not only that, Hike supports more than 40 vernacular Indian languages including stickers for all of them. 

“AI can create value in terms of increasing the engagement of the user on a platform by providing interesting chatbots that can excite the users. Also, providing the right context-driven and personalised message recommendations, sticker recommendations, having the right set of campaigns, understanding the behaviour of the user in an anonymised and secure manner can help users get the best of the platform, ” said Narang. 

Source: Hike.in

Narang says that by using TensorFlow and TensorFlow Lite, it has brought in the hyper-personal and hyper-local elements in messaging by addressing numerous Indian languages. Here, the messenger does personalised stickers with low latency making it easy to use. Users have lauded the company’s efforts on social media with one user saying he learnt Bengali just by using Hike Stickers. 

Hike’s sticker recommendation engines make Hike an intersection of art, messaging and personalised chat options. It is one of the few companies in the country that is using NLP to solve for local languages at a mass scale using the work behind Sticker Recommendations and AI-driven innovations.

Hike’s Sticker recommendation works in three ways:

  • Sticker Suggestion which gets the right sticker at the right time as a user types.
  • Quick Reply where a user can tap on any sticker received to reply with a relevant sticker quickly.
  • Quick Follow where a user can tap on any sticker sent earlier to then follow up with a relevant sticker instantly

“We want users being able to express themselves through stickers and being able to do that using AI is really helpful. All the innovations, whether they apply on the consumer side in terms of outward-facing and inward-facing in terms of core engineering stack where AI is used, can help you give the optimisation, ” Narang said.

More Great AIM Stories

Vishal Chawla
Vishal Chawla is a senior tech journalist at Analytics India Magazine and writes about AI, data analytics, cybersecurity, cloud computing, and blockchain. Vishal also hosts AIM's video podcast called Simulated Reality- featuring tech leaders, AI experts, and innovative startups of India.

More Stories

OUR UPCOMING EVENTS

8th April | In-person Conference | Hotel Radisson Blue, Bangalore

Organized by Analytics India Magazine

View Event >>

30th Apr | Virtual conference

Organized by Analytics India Magazine

View Event >>

MORE FROM AIM
Vijaysinh Lendave
NeuSpell: A Neural Net Based Spelling Correction Toolkit

Spell check features, or spell checkers, are software applications that check words against a digital dictionary to ensure they are correctly spelled. Words that are identified as misspelled by the spell checker are usually highlighted or underlined.

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

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

Subscribe to our newsletter

Get the latest updates from AIM