Kwame for Science: An AI Teaching Assistant Based on Sentence-BERT for Science Education in West Africa
This work addresses the challenge of scalable and cost-effective remote science education for students in West Africa, though it is incremental as an adaptation of a previous system.
The paper tackled the problem of limited teacher access in African science education by developing Kwame for Science, an AI teaching assistant based on Sentence-BERT, which achieved a top 3 accuracy of 87.5% in a real-world deployment with 190 users across 11 countries.
Africa has a high student-to-teacher ratio which limits students' access to teachers. Consequently, students struggle to get answers to their questions. In this work, we extended Kwame, our previous AI teaching assistant, adapted it for science education, and deployed it as a web app. Kwame for Science answers questions of students based on the Integrated Science subject of the West African Senior Secondary Certificate Examination (WASSCE). Kwame for Science is a Sentence-BERT-based question-answering web app that displays 3 paragraphs as answers along with a confidence score in response to science questions. Additionally, it displays the top 5 related past exam questions and their answers in addition to the 3 paragraphs. Our preliminary evaluation of the Kwame for Science with a 2.5-week real-world deployment showed a top 3 accuracy of 87.5% (n=56) with 190 users across 11 countries. Kwame for Science will enable the delivery of scalable, cost-effective, and quality remote education to millions of people across Africa.