Overview

Code for Good 2023, is a 36-hour Duke-hosted annual hackathon for social good. Our project, CodeLingo, won 1st place for the Education Track. As the team's designer, I led secondary research/design ideation and had fun helping out with front-end here and there.

Background

Learning to code is significantly harder for non-native English speakers. Why? Not surprisingly, English is the dominant language for not only documentation but also for reporting/ filing bugs. Even less surprisingly, it's been found that children learn to code faster in their native language→ than in English.

That's the reasoning behind CodeLingo - an AI ed-tech platform for non-native English speakers learning to code, built using OpenAI's GPT-3.5 and DeepL's translator API.

While CodeLingo's primary goal is to make it easier for non-native English speakers to learn to code in their native language, there is also a use case for English speakers working abroad! While interning at a small startup in South Korea in 2021, I worked on a team with engineers from Spain, the US, and South Korea, with Korean as our common language. As a non-native Korean speaker, it would have been extremely helpful to have a platform like CodeLingo to establish a shared understanding of programming fundamentals in Korean rather than English.

Big shoutout to each of my team members and thank you to all the HackDuke organizers who made this incredible experience possible!