Enhancing Quality of Experience in Wireless English Education Platforms via Predictive Large Models

Abstract

This work presents a Predictive Large Model-Driven Framework (PLMF) for Wireless English Education Platforms (WEEPs) that integrates real-time Quality of Experience (QoE) forecasting, CEFR-aware semantic simplification, and adaptive content delivery in a unified, feedback-driven architecture. To support system evaluation, we construct EduQoE-PLMF, a multimodal dataset comprising CEFR-tagged content, simulated network traces, behavioral logs, and user-rated QoE labels. PLMF is benchmarked against five representative baselines across three key tasks. Experimental results show that PLMF achieves superior performance in QoE prediction (MSE: 0.025, R²: 0.89), content simplification (SARI: 44.9, Readability: 2.9), and learner engagement (TCR: 83.2%, DR: 11.4%, SSS: 4.3). Ablation studies and heatmap analysis further reveal the complementary value of each system module. These findings demonstrate the effectiveness of combining predictive reasoning, personalization, and delivery optimization to enable robust and learner-centered wireless education systems.