A Machine Learning based Intelligent Evaluation Technique for Information Literacy of Foreign Language Teachers

Assessing information literacy of foreign language teachers is critical in improving teaching effectiveness and academic achievement. Current assessment frameworks, however, depend on qualitative surveys and conventional statistical models that are not flexible and not accurate. Conventional models, including rule-based and linear regression models, cannot identify nonlinear relationships among complex literacy indicators. This paper proposes a Radial Basis Function (RBF)-based deep learning model to overcome such constraints. The proposed model is efficient in handling intricate, multidimensional data with high generalization and increased convergence. Comparative study against conventional backpropagation neural networks and support vector machines shows the excellence of the proposed RBF model in performance with 96.2% accuracy and 95.8% F1-score, being superior to others by 6–10%. The system takes information behaviour measures, digital resource use, and cognitive ability indices as input parameters. The performance mechanism guarantees interpretability and stability and is thus an effective instrument for dynamic and data-driven literacy assessment. This methodology not only improves the accuracy of assessments but also facilitates targeted intervention training for educators.