Integrating Hybrid Ensemble Models for Predicting Risk Reduction in Children's Digital Literacy

Abstract

The rapid growth of digital engagement among children has amplified both opportunities for learning and exposure to significant risks. While digital literacy (DL) equips children with essential competencies to navigate online environments, it does not inherently guarantee safety, particularly when mediation from parents or educators remains reactive rather than preventive. This study proposes a novel predictive framework integrating Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and ensemble learning to model the interactions among DL, mediation, and risk. Exploratory statistical analysis revealed weak to moderate correlations, suggesting complex, nonlinear interdependencies that cannot be captured by linear models alone. PCA confirmed that risk and mediation strongly co-vary, whereas DL emerges as a distinct dimension. Baseline results showed that ANFIS outperformed ANN in handling fuzzy and uncertain relationships, achieving stronger correlations and lower error margins. However, ensemble approaches significantly improved predictive performance, with Ensemble-ANN achieving near-perfect accuracy (R = 0.999, RMSE < 0.0001), demonstrating its robustness and generalizability. The physical interpretation highlights DL as a double-edged sword, simultaneously empowering children while increasing exposure to risks, and underscores the need for mediation strategies that are proactive rather than reactive. Importantly, the findings align with international frameworks, including UNICEF’s Child Online Protection (COP), UNESCO’s Global Digital Literacy Framework, OECD’s socio-technical safeguards, and WHO’s digital health guidelines. This alignment reinforces the study’s contribution beyond computational advances, offering evidence-based insights for educators, parents, and policymakers seeking to balance empowerment and protection in children’s digital ecosystems.