Skip to main content Skip to navigation

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

Project Overview

The document explores the use of generative AI in education through the development of the 21st Century Teacher Educator AI tool, specifically tailored for pre-service teachers in Ghana. This innovative tool is designed to enhance educational support by incorporating local cultural, linguistic, and curricular elements, thereby promoting self-directed learning and critical thinking among future educators. It addresses the unique educational challenges encountered in the Global South, such as data underrepresentation and the necessity for language adaptation, while emphasizing the ongoing need for the refinement of AI models to better serve these contexts. The document also discusses potential solutions for effectively integrating AI into education, aiming to improve teaching practices and learning outcomes for teachers and students alike. Overall, it highlights the transformative potential of generative AI in addressing the specific needs of educators in developing regions.

Key Applications

21st Century Teacher Educator AI tool for Ghana

Context: Designed for pre-service teachers in Ghana, supporting their education and training.

Implementation: Developed using OpenAI’s Retrieval-Augmented Generation framework and Interactive Semi-Automated Prompting Strategy, incorporating localized datasets and cultural frameworks.

Outcomes: Provides context-specific resources, enhances self-directed learning, supports bilingual instruction, and aligns educational content with Ghana's National Teacher Education Curriculum Framework.

Challenges: Occasional inaccuracies (hallucinations) in content generation, especially in underrepresented local languages, and subscription costs for full access.

Implementation Barriers

Technical

Inaccuracies in AI-generated content, particularly in local languages.

Proposed Solutions: Continuous model refinement and the integration of high-quality, contextually relevant datasets.

Accessibility

Subscription costs limit full access to the AI tool for pre-service teachers.

Proposed Solutions: Collaboration with OpenAI's NextGen initiative to expand access to educational institutions.

Project Team

Matthew Nyaaba

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Matthew Nyaaba

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies