Geo-spatial Analysis of AI Deployment in Education: Identifying Patterns and Predictors of Adoption in Southeast Nigeria
Ezinne Okoroafor *
Department of Geography and Environmental Sustainability, Faculty of Social and Management Sciences, Alvan Ikoku Federal University of Education, Owerri, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
The rapid evolution of Artificial Intelligence (AI) technologies is transforming global education systems, offering innovative pathways for personalized learning, administrative efficiency, and intelligent content delivery. However, disparities in regional adoption, particularly in developing contexts, remain a pressing concern. This study aims to explore the spatial distribution, intensity, and key determinants of AI integration in educational institutions across the southeastern geopolitical zone of Nigeria. Given the socio-economic and infrastructural heterogeneity of this region, a geo-spatial analytical approach will be chosen to unravel not just whether AI is being adopted, but where and why disparities exist. A convergent mixed-methods design will be employed, combining quantitative spatial analysis with qualitative inquiry to provide both breadth and depth. Using Geographic Information Systems (GIS) and remote sensing data, AI deployment patterns will be mapped to visualize adoption hotspots and lagging areas. This will be complemented by institutional surveys and interviews with education stakeholders to uncover contextual drivers and inhibitors of adoption. The choice of GIS is rooted in its capacity to spatially contextualize data, allowing for pattern recognition that would be obscured in non-spatial datasets. Quantitative data will be analyzed using the Statistical Package for the Social Sciences (SPSS) for descriptive statistics, and R programming for more advanced inferential analyses. Specifically, multiple regression, logistic regression, and Geographically Weighted Regression (GWR) will also be used to identify predictors of AI adoption such as infrastructure quality, access to digital tools, institutional policy readiness, educator digital competence, and urban-rural divide. By identifying the geospatial and systemic factors influencing AI adoption, this study provides actionable insights for policymakers, education administrators, and technology providers. It advocates for targeted interventions that address regional disparities, foster digital equity, and promote scalable AI integration strategies tailored to local realities.
Keywords: Artificial intelligence in education, geo-spatial analysis, Southeast Nigeria, predictors of adoption, educational technology deployment