Context-Aware Explainable Adaptive Learning Framework for Large Classroom Management in Resource-Constrained African Universities

ABSTRACT

Rising enrolment in higher-education institutions across developing countries has intensified persistent
challenges in classroom management, learner engagement, and personalized instruction. Most existing
adaptive learning systems are designed for stable, well-resourced environments, rendering them largely
ineffective in resource-constrained African universities. This study proposes a Context-Aware Explainable
Adaptive Learning Framework (CAELF) developed through design-based conceptual research. The
framework synthesizes adaptive learning theory, explainable artificial intelligence (XAI) principles,
context-aware computing, and human-centred instructional design into a six-layer architecture. Its defining
feature is the treatment of environmental variables such as internet instability, limited device access, and
participation irregularities as core inputs to adaptive decision-making. Embedded explainability
mechanisms provide learners and lecturers with transparent, actionable reasoning behind system outputs,
strengthening pedagogical trust and accountability. The study contributes to educational technology
scholarship by unifying contextual responsiveness, transparency, scalability, and human-centred oversight
within a single model tailored to large, under-resourced African classroom environments.

KEYWORDS

Adaptive Learning, Explainable Artificial Intelligence, Context-Aware Educational Systems, ResourceConstrained Higher Education, African Universities

PDF LINK: aircconline.com

VOLUME LINK: airccse.org

MORE DETAILS: airccse.org