DESIGNING AI-DRIVEN PERSONALIZED LEARNING ECOSYSTEMS IN HIGHER EDUCATION: PATHWAYS TO EQUITABLE ACCESS AND THE ACHIEVEMENT OF SDG 4 IN EMERGING ECONOMIES
Keywords:
Artificial Intelligence, Personalized Learning, Higher Education, Educational Equity, SDG 4Abstract
This study examined the design and implementation of artificial intelligence-driven personalized learning ecosystems as a pathway to equitable access and the achievement of Sustainable Development Goal 4 in higher education within emerging economies, guided by four research questions and four null hypotheses. A mixed-methods explanatory design was adopted, targeting a population of 8,420 undergraduate students and 312 academic staff across three public universities in South-East Nigeria, namely: University of Nigeria, Nsukka (UNN); Nnamdi Azikiwe University, Awka (NAU); and Enugu State University of Science and Technology (ESUT), from which a sample of 469 respondents was drawn using stratified and purposive sampling techniques. Data were collected using a structured questionnaire, semi-structured interviews, and institutional learning analytics; content and construct validity were ensured through expert review, and reliability was assessed using a Cronbach’s alpha coefficient of 0.86. Data collection was conducted over a twelve-week period, and analysis employed descriptive statistics, independent t-tests, regression analysis, and one-way ANOVA at a 0.05 level of significance. Findings revealed that AI-driven personalization significantly improved student engagement, retention, and academic performance, although infrastructural constraints, uneven digital literacy, and institutional readiness moderated these outcomes. The results indicate that AI systems can enhance educational equity when embedded within context-sensitive frameworks supported by ethical governance and institutional capacity. The study recommends sustained investment in digital infrastructure, targeted faculty development, and policy frameworks for responsible AI integration. A key limitation is the restriction to three institutions, while future research should adopt longitudinal and cross-national designs.Downloads
Published
22-04-2026
How to Cite
Ani, A. N. A., Anachuna, O. N., Ezenwagu, S. A., Eziamaka, C. N., Chukwu, R. N., & Chibuko, H. (2026). DESIGNING AI-DRIVEN PERSONALIZED LEARNING ECOSYSTEMS IN HIGHER EDUCATION: PATHWAYS TO EQUITABLE ACCESS AND THE ACHIEVEMENT OF SDG 4 IN EMERGING ECONOMIES. International Journal of Premium Advanced Educational Research, 2(4), 39–50. Retrieved from https://www.ijpaer.org/index.php/IJPAER/article/view/85
Issue
Section
Articles