Problem
Research questions and friction points this paper is trying to address.
teacher professional development
low-resource contexts
AI in education
digital inclusion
mobile platforms
Teacher Professional Development on WhatsApp and LLMs: Early Lessons from Cameroon
🤖 AI Summary
This study addresses the challenge of delivering effective teacher professional development in resource-constrained settings, where educators often rely on lightweight mobile platforms like WhatsApp yet struggle with conventional online programs. Conducting a field pilot in Cameroon, the research introduces a novel “reflective AI” design paradigm tailored for low-resource contexts by embedding large language model (LLM)-driven professional development content within a WhatsApp chatbot, contextualized through bilingual (English–French) support and local cultural relevance. A mixed-methods evaluation reveals that, compared to standard online forms, the chatbot significantly enhances usability and user experience while achieving comparable learning outcomes. Despite constraints related to connectivity, data costs, and bilingual demands, the findings demonstrate the feasibility and promise of lightweight AI-mediated educational interventions in underserved regions.
📝 Abstract
AI in education is commonly delivered through web-based systems such as online forms and institutional platforms. However, these approaches can exclude teachers in low-resource contexts, where everyday mobile platforms like WhatsApp serve as primary digital infrastructure. To address this gap, we present a field pilot in Cameroon that deploys a WhatsApp-based chatbot with LLM-supported content for teacher professional development (TPD), compared with an online form baseline. The system was evaluated through a mixed-methods study with 47 primary school teachers, integrating quantitative measures with qualitative insights from interviews and participant feedback. Results show that the chatbot was rated higher in perceived usability and overall experience, while learnability remained comparable. These improvements were driven by platform familiarity, low interaction overhead, and the modular structure of LLM-supported content, but were constrained by connectivity limitations, prepaid data costs, and multilingual needs (English/French). Building on these findings, we outline design directions for multilingual, culturally grounded interaction and for supporting prompting and reflection in AI use. More broadly, this work points to Thoughtful AI that supports reflection, relevance, and sustained professional growth.
Innovation
Methods, ideas, or system contributions that make the work stand out.
WhatsApp-based chatbot
Large Language Models (LLMs)
Teacher Professional Development
Low-resource contexts
Thoughtful AI
🔎 Similar Papers
No similar papers found.
