EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Big Data-Enabled Adaptive Graph Neural Models for Intelligent English Learning Performance Assessment

Zhenxiao Zhang

Data and Metadata · 13.03.2026 · 5 · 791

DOI: 10.56294/dm2026791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 13.03.2026. Verfasst von Zhenxiao Zhang. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The rapid growth of online English learning platforms has generated large volumes of heterogeneous learner behavior data, creating opportunities for personalized education. However, traditional learning analytics methods fail to capture the complex interactions among learners, learning activities, and learning resources, which limits prediction accuracy and adaptive learning in big data environments.

Objective

The reserach proposes an Artificial Intelligence (AI)-driven English Learning Behavior Model based on an Adaptive Dandelion Graph Neural Network (AdapDan-GNet) to comprehensively model learner behavior and accurately predict English learning performance by capturing relational and temporal dependencies in large-scale learning data.

Method

Learning data were collected from digital platforms, including clickstream logs, session durations, assessment scores, and learner feedback. The data were preprocessed through cleaning and normalization to ensure quality and scalability. Principal Component Analysis (PCA) was applied for dimensionality reduction while preserving informative behavioral patterns. The extracted features were structured as graph nodes representing learners, learning activities, and learning resources. AdapDan-GNet employed adaptive dandelion-based graph propagation for efficient information diffusion and dynamic neighborhood learning.

Results

Experimental results demonstrate that AdapDan-GNet achieved a prediction accuracy of 97,60 % [Rev1.1][user1.2], outperforming traditional machine learning and deep learning models in terms of accuracy and adaptability. The framework was implemented using Python 3.1 and showed stable performance on large-scale English learning data.

Conclusions

The integration of big data analytics with adaptive graph neural networks provides a scalable and effective solution for personalized English language learning. AdapDan-GNet enhances prediction performance, learner engagement, and overall learning outcomes by modeling complex relational and temporal learner behaviors.

Zitieren

APA

Zhang, Z. (2026). Big Data-Enabled Adaptive Graph Neural Models for Intelligent English Learning Performance Assessment. Data and Metadata, 5, 791. https://doi.org/10.56294/dm2026791

Vancouver

Zhang Z. Big Data-Enabled Adaptive Graph Neural Models for Intelligent English Learning Performance Assessment. Data and Metadata. 2026;5:791. doi:10.56294/dm2026791

BibTeX
@article{Zhang2026,
  author = {Zhang, Zhenxiao},
  title = {Big Data-Enabled Adaptive Graph Neural Models for Intelligent English Learning Performance Assessment},
  journal = {Data and Metadata},
  year = {2026},
  volume = {5},
  pages = {791},
  doi = {10.56294/dm2026791}
}
Kostenlos starten →