Developing NLP-based English learning applications for the Vietnamese market

Explore more case study

Background

In recent years, the market English-learning apps has seen steady growth, which can be attributed to several key factors. First, the widespread use of smartphones has vastly changed language learning by making it possible almost anytime and anywhere. The COVID-19 pandemic further accelerated this trend, as restrictions and the shift towards remote education led more people to turn to digital platforms for learning languages.  

Second, globalization has amplified the demand for English proficiency in the workforce, making it a key asset in international business. This shift has driven individuals towards English-learning apps as essential tools for career advancement in a globally connected market. 

The client is a rising player in the SaaS sector in Vietnam. They set an ambitious goal to develop a family of NLP-based English learning apps for Vietnamese people. Each application in the family targets a different market: for adult learners, young children, and educational institutions and English centers.  

Telecommunication

Challenges

GEM’s team had to resolve several issues both before and after the app was launched. 

Before launching:  

The client asked GEM to develop a system that could provide rapid and accurate feedback to learners. Personalization was also a must-have feature, as they wanted the app to adapt the learning process to each learner’s pace and level to maintain user engagement and foster positive learning outcomes.   

After launching:  

First, the app received several user feedback saying that it was hard to remember their login details, as there were too many login options to choose from (Google, Apple ID, Facebook, Phone number, Email, etc.). This variation of options, while intended to provide convenience, led to confusion for users, which underscored the need for a more streamlined sign-in process. 

In addition, the Google AI service, which was used for reading and analyzing users’ speech samples to provide feedback, resulted in higher operational costs than anticipated. 

Artificial Intelligence (AI)
Data Analytics & Business Intelligence
tele
Data Analytics & Business Intelligence

Solution 

To meet the client’s requirement for personalization and automation, GEM implemented NLP technology to enable shadowing and modeling exercises within the app. Thanks to NLP, the app can analyze the user’s speech to identify spelling mistakes and suggest improvements. Therefore, it can help users fix their pronunciation in a much shorter time and improve their fluency. Adopting AI algorithms also allowed the solution to tailor the learning experience to each user’s pace and proficiency level aligns 

To tackle the login problem, our team decided to simplify the process by reducing the number of login options, believing that less is more when it comes to user convenience. Now, the app offers just two login methods, making the login process smoother and more user-friendly. 

To reduce the high costs associated with the Google AI speech service, we switched to using pre-recorded speeches. This move significantly lowered the operational costs. 

Tech stack

  • Android Native, iOS 
  • Swift 
  • Spring, Java, Servlet 
  • PostgresDB 
  • Ocean Digital 

 Output 

  • NLP-based shadowing and modeling exercises 
  • Personalized learning content based on daily conversation context 
  • Timely reports to review learning progress 
  • Registration on the mobile app or via SMS  
  • Premium account activation through codes  
  • English learning games, flashcards, songs and videos, and coloring exercises based on different age groups 
  • Parent/Teacher accounts to monitor and support children’s learning 

Impacts 

With the successful launch of the apps for adults and children, the client was impressed with our delivery speed and quality. The app supporting schoolwork was also ready to launch and prepare for partnership with schools in Vietnam. 

Currently, on Google Play Store, the app for adults has more than 5000 downloads with a 4.3 stars rating. On the App Store, it was rated 4.6 by users. Meanwhile, the one for kids has more than 1000 downloads on Google Play Store, with 4.6 stars rating on Apple and Google Stores. 

Closing remarks

This case study highlights how GEM leveraged our tech tools and expertise to deliver satisfactory app solutions and address development challenges. The favorable reception of the apps, as shown in high download numbers and ratings, further affirms the effectiveness and user-centricity of our approach.