Graph neural network-based personalized English learning path planning
Abstract
Personalized English learning requires adaptive systems that tailor learning paths to individual learners’ knowledge, preferences, and performance. This research proposes a neural network-based approach for personalized English learning path planning, modelling the dependencies between language concepts, learner proficiency, and performance data as a graph structure. In this model, nodes represent individual learners, while edges connect learners with similar learning characteristics using a k-Nearest Neighbour (kNN) graph constructed from proficiency level, engagement, quiz performance, mastery level, vocabulary complexity, and learning objectives. The Fish School Search-Driven Attention-Enriched Graph Neural Network (FSS-Att-GNN) processes these relationships to predict the optimal sequence of learning resources and path plan for each learner, dynamically adjusting recommendations based on ongoing performance and feedback. The proposed system incorporates multiple learner-specific variables, including vocabulary complexity, proficiency level, and learning objectives, enabling highly tailored learning paths. The English Learning Path dataset contains 4000 learner samples with features including proficiency, engagement, quiz performance, and learning path labels for analysis. Preprocessing included Min–Max normalization, label encoding, and Interquartile Range (IQR)-based outlier removal to standardize numerical features, encode categories, and eliminate noisy data points. A kNN graph constructs learner similarity relationships using distance metrics, enabling effective graph-based personalized learning path analysis and recommendation. Python implementation of the proposed FSS-Att-GNN achieved 98.60% accuracy, outperforming baseline models in personalized learning path prediction. The findings suggest that GNN-based personalized learning systems can significantly enhance English learning efficiency, comprehension, and motivation, providing a foundation for intelligent, data-driven educational platforms.