Samuel Boateng

George Boateng, Samuel John, Samuel Boateng et al.

Africa has a high student-to-teacher ratio which limits students' access to teachers for learning support such as educational question answering. In this work, we extended Kwame, a bilingual AI teaching assistant for coding education, adapted it for science education, and deployed it as a web app. Kwame for Science provides passages from well-curated knowledge sources and related past national exam questions as answers to questions from students based on the Integrated Science subject of the West African Senior Secondary Certificate Examination (WASSCE). Furthermore, students can view past national exam questions along with their answers and filter by year, question type, and topics that were automatically categorized by a topic detection model which we developed (91% unweighted average recall). We deployed Kwame for Science in the real world over 8 months and had 750 users across 32 countries (15 in Africa) and 1.5K questions asked. Our evaluation showed an 87.2% top 3 accuracy (n=109 questions) implying that Kwame for Science has a high chance of giving at least one useful answer among the 3 displayed. We categorized the reasons the model incorrectly answered questions to provide insights for future improvements. We also share challenges and lessons with the development, deployment, and human-computer interaction component of such a tool to enable other researchers to deploy similar tools. With a first-of-its-kind tool within the African context, Kwame for Science has the potential to enable the delivery of scalable, cost-effective, and quality remote education to millions of people across Africa.

George Boateng, Samuel John, Andrew Glago et al.

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.

George Boateng, Samuel Boateng, Victor Kumbol

Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.

Prince Steven Annor, Samuel Boateng, Edwin Pelpuo Kayang et al.

Automatic grading systems have been in existence since the turn of the half-century. Several systems have been developed in the literature with either static analysis and dynamic analysis or a hybrid of both methodologies for computer science courses. This paper presents AutoGrad, a novel portable cross-platform automatic grading system for graphical Processing programs developed on Android smartphones during an online course. AutoGrad uses Processing, which is used in the emerging Interactive Media Arts, and pioneers grading systems utilized outside the sciences to assist tuition in the Arts. It also represents the first system built and tested in an African context across over thirty-five countries across the continent. This paper first explores the design and implementation of AutoGrad. AutoGrad employs APIs to download the assignments from the course platform, performs static and dynamic analysis on the assignment to evaluate the graphical output of the program, and returns the grade and feedback to the student. It then evaluates AutoGrad by analyzing data collected from the two online cohorts of 1000+ students of our SuaCode smartphone-based course. From the analysis and students' feedback, AutoGrad is shown to be adequate for automatic assessment, feedback provision to students, and easy integration for both cloud and standalone usage by reducing the time and effort required in grading the 4 assignments required to complete the course.