Graph neural network-based personalized English learning path planning

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.

Authors

Institutions

Publication Details

Journal
Discover Artificial Intelligence
Published
2026-11-19
DOI
https://doi.org/10.1007/s44163-026-02190-3
Primary Topic
Intelligent Tutoring Systems and Adaptive Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Graph neural network-based personalized English learning path planning

Jiabao Wang
Discover Artificial Intelligence
Intelligent Tutoring Systems and Adaptive Learning
article

Graph neural network-based personalized English learning path planning

Jiabao Wang
article en

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.

Discover Artificial IntelligenceVol. 6(1)
South China Business College Guangdong University of Foreign Studies (CN)
Intelligent Tutoring Systems and Adaptive Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon