EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework

Xiaoyi Zhang, Yakang Zhang, Angelina Lilac Chen, Manning Yu, Lihao Zhang iD

PLOS ONE · 22.01.2025 · 20 (1) · e0314823

DOI: 10.1371/journal.pone.0314823 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 22.01.2025. Verfasst von Xiaoyi Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Liberal Arts and Science, University of Illinois Urbana-Champaign, Urbana, IL, United States of America. Hauptthemen laut MEDLINE: Deep Learning, Students, Academic Performance, Educational Measurement. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As education increasingly relies on data-driven methodologies, accurately predicting student performance is essential for implementing timely and effective interventions. The California Student Performance Dataset offers a distinctive basis for analyzing complex elements that affect educational results, such as student demographics, academic behaviours, and emotional health. This study presents the GNN-Transformer-InceptionNet (GNN-TINet) model to overcome the constraints of prior models that fail to effectively capture intricate interactions in multi-label contexts, where students may display numerous performance categories concurrently. The GNN-TINet utilizes InceptionNet, transformer architectures, and graph neural networks (GNN) to improve precision in multi-label student performance forecasting. Advanced preprocessing approaches, such as Contextual Frequency Encoding (CFI) and Contextual Adaptive Imputation (CAI), were used on a dataset of 97,000 occurrences. The model achieved exceptional outcomes, exceeding current standards with a Predictive Consistency Score (PCS) of 0.92 and an accuracy of 98.5%. Exploratory data analysis revealed significant relationships between GPA, homework completion, and parental involvement, emphasizing the complex nature of academic achievement. The results illustrate the GNN-TINet’s potential to identify at-risk pupils, providing a robust resource for educators and policymakers to improve learning outcomes. This study enhances educational data mining by enabling focused interventions that promote educational equality, tackling significant challenges in the domain.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningStudentsAcademic PerformanceEducational MeasurementHumansNeural Networks, ComputerFemaleMaleCalifornia

Autor:innen und Institutionen

  • College of Liberal Arts and Science, University of Illinois Urbana-Champaign, Urbana, IL, United States of America.
  • Industrial Engineering and Operations Research Department, Columbia University, New York, NY, United States of America.
  • Le Regent School, Crans-Montana, Switzerland.
  • Department of Statistics, Columbia University, New York, NY, United States of America.
  • Department of Information Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, China.

ORCID-Profile: Lihao Zhang

Zitieren

APA

Zhang, X., Zhang, Y., Chen, A. L., Yu, M., & Zhang, L. (2025). Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework. PLOS ONE, 20(1), e0314823. https://doi.org/10.1371/journal.pone.0314823

Vancouver

Zhang X, Zhang Y, Chen AL, Yu M, Zhang L. Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework. PLOS ONE. 2025;20(1):e0314823. doi:10.1371/journal.pone.0314823

BibTeX
@article{Zhang2025,
  author = {Zhang, Xiaoyi and Zhang, Yakang and Chen, Angelina Lilac and Yu, Manning and Zhang, Lihao},
  title = {Optimizing multi label student performance prediction with GNN-TINet: A contextual multidimensional deep learning framework},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {1},
  pages = {e0314823},
  doi = {10.1371/journal.pone.0314823}
}
Kostenlos starten →