Glocalizing Generative AI in Education for the Global South: The Design Case of 21st Century Teacher Educator AI for Ghana

2025-04-09

AI Summary

This study addresses the lack of localized generative AI tools in Ghana’s pre-service teacher education. We designed and implemented a bilingual AI teaching assistant aligned with local languages, cultural contexts, and Ghana’s National Teacher Education Curriculum Framework (NTECF). Methodologically, we introduced a “glocalized” design paradigm integrating a culturally responsive generative AI framework (GenAI-CRSciA) with anti-neocolonial AI principles; built upon OpenAI’s RAG architecture; employed an interactive semi-automatic prompting strategy (ISA); and incorporated UNESCO’s AI ethics guidelines alongside multilingual Ghanaian educational corpora (English, Twi, Dagbani, etc.). Contributions include: (1) the first systematic integration of ethical alignment, curriculum fidelity, and sociolinguistic-cultural adaptation in an African teacher education context; (2) support for bilingual pedagogical resource and action research guide generation; and (3) pilot validation demonstrating high linguistic adaptability while revealing the mechanistic relationship between corpus scale and hallucination rates.

Technology Category

• Philosophy and Ethics of AI: Artificial General Intelligence
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Humans and AI: AI for Accessibility

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

This study presents the design and development of the 21st Century Teacher Educator for Ghana GPT, a customized Generative AI (GenAI) tool created using OpenAI's Retrieval-Augmented Generation (RAG) and Interactive Semi-Automated Prompting Strategy (ISA). Anchored in a Glocalized design approach, this tool supports pre-service teachers (PSTs) in Ghana by embedding localized linguistic, cultural, and curricular content within globally aligned principles of ethical and responsible AI use. The model utilizes structured, preloaded datasets-including Ghana's National Teacher Education Curriculum Framework (NTECF), UNESCO's (2023) AI guidelines, and culturally responsive pedagogies-to offer curriculum-aligned, linguistically adaptive, and pedagogically grounded learning support. The ISA enables users to input their institution, year, and semester, generating tailored academic content such as lecture notes, assessment practice, practicum resources, and action research guidance. The design incorporates the Culture and Context-Aware Framework, GenAI-CRSciA, and frameworks addressing GenAI neocolonialism to ensure equity, curriculum fidelity, and local relevance. Pilot implementation revealed notable strengths in language adaptation and localization, delivering bilingual support in English and Ghanaian languages like Twi, Dagbani, Mampruli, and Dagaare, with contextualized examples for deeper understanding. The GPT also generated practice assessments aligned with course objectives, reinforcing learner engagement. Challenges included occasional hallucinations due to limited corpora in some indigenous languages and access barriers tied to premium subscriptions. This design case contributes to discourse on Glocalized GenAI and calls for collaboration with OpenAI NextGen to expand access and empirically assess usage across diverse African educational contexts.

Problem

• Developing localized GenAI tool for Ghanaian teacher education
• Addressing linguistic and cultural gaps in AI educational support
• Mitigating GenAI neocolonialism through glocalized design frameworks

Innovation

• Uses Retrieval-Augmented Generation for localized content
• Incorporates Interactive Semi-Automated Prompting Strategy
• Integrates Culture and Context-Aware Framework