Kwame: A Bilingual AI Teaching Assistant for Online SuaCode Courses

TL;DR

Kwame is a bilingual AI teaching assistant designed for online coding courses in Africa, providing accurate answers in English and French to support students' learning in a multilingual environment.

Contribution

This work introduces Kwame, a novel bilingual AI TA for online coding courses, trained on course-specific data to improve student support in multilingual contexts.

Findings

Fine-tuning on course data improves accuracy

Top 3 and 5 answer retrieval enhances performance

Kwame outperforms TF-IDF and Universal Sentence Encoder

Abstract

Introductory hands-on courses such as our smartphone-based coding course, SuaCode require a lot of support for students to accomplish learning goals. Online environments make it even more difficult to get assistance especially more recently because of COVID-19. Given the multilingual context of SuaCode students - learners across 42 African countries that are mostly Anglophone or Francophone - in this work, we developed a bilingual Artificial Intelligence (AI) Teaching Assistant (TA) - Kwame - that provides answers to students' coding questions from SuaCode courses in English and French. Kwame is a Sentence-BERT (SBERT)-based question-answering (QA) system that we trained and evaluated offline using question-answer pairs created from the course's quizzes, lesson notes and students' questions in past cohorts. Kwame finds the paragraph most semantically similar to the question via cosine similarity. We compared the system with TF-IDF and Universal Sentence Encoder. Our results showed that fine-tuning on the course data and returning the top 3 and 5 answers improved the accuracy results. Kwame will make it easy for students to get quick and accurate answers to questions in SuaCode courses.