A Systematic Review on Explainable AI for Spatial Classification of Digital Readiness in Secondary Schools

Abstract

This systematic review examines how machine learning, particularly explainable AI (XAI), is used to classify digital readiness in secondary schools within underdeveloped regions. A total of 50 peer-reviewed studies published between 2022 and 2025 were analyzed to identify dominant models, feature indicators, and the use of spatial data. The results show that XGBoost and Random Forest are widely applied, but explainable methods such as SHAP and spatial classification remain limited. This gap hinders the development of interpretable and regionally sensitive assessments. Based on the synthesis, this study proposes an integrated framework combining XAI and spatial mapping to enhance readiness classification and support data-driven educational policy.

Ähnliche Arbeiten