Adesua: WhatsApp AI bot delivers 93.75% useful science help in West Africa

Sub-Saharan Africa faces severe teacher shortages and high student-teacher ratios, limiting access to personalized learning and formative assessment. To address this, researchers from multiple institutions developed Adesua—a WhatsApp-based AI Teaching Assistant for science education, extending the Kwame for Science platform. Adesua leverages WhatsApp's massive adoption in Africa to deliver curriculum-aligned support to Junior and Senior High School students in West Africa. The system combines curated textbooks and 33 years of national exam questions with generative AI, enabling conversational question answering and automated assessment with feedback. Students can ask science questions, take timed or untimed multiple-choice tests by topic or exam year, and receive instant grading with detailed explanations for both correct and incorrect answers.

A 6-month feasibility deployment in 2025 involved 56 active users in Ghana, including students and parents. Quantitative evaluation showed high perceived usefulness, with a 93.75% helpfulness score for AI-generated answers (though only 16 ratings). These preliminary results suggest WhatsApp-based AI assistants could offer scalable, low-cost personalized learning in resource-constrained contexts. The study was accepted at the 27th International Conference on Artificial Intelligence in Education (AIED 2026). While the sample size is small, the approach demonstrates a practical pathway to bridge educational gaps using widely available mobile technology.