EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BERT-Enhanced HyperGAT with Siamese Networks and Reference Answer Set for Automated Short-Answer Scoring

Chen Liu, Xiaofen Wan, Zhihao Ni, Sheng Su iD, Chunhua Kang iD

Behavioral Sciences · 09.06.2026 · 16 (6) · 946

DOI: 10.3390/bs16060946 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Behavioral Sciences, online erschienen am 09.06.2026. Verfasst von Chen Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Philosophy and Social Science Laboratory for the Mental Health and Crisis Intervention of Children and Adolescents, Zhejiang Normal Universi…. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Humanities and Social Sciences Fund of the Ministry of Education, Zhejiang Philosophy and Social Science Laboratory for the Mental Health and Crisis Intervention of Children and Adolescents.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a novel framework, HyperGAT-BERT-RAS, that integrates (1) a HyperGraph Attention Network (HyperGAT) with BERT for enhanced semantic representation; (2) a Reference Answer Set (RAS) constructed via clustering of full-score answers; and (3) Siamese Neural Networks (SNNs) for similarity-based scoring. Experiments on the Ohsumed and ASAP-5 datasets demonstrate that (i) HyperGAT-BERT achieves 72.95% accuracy on Ohsumed text classification, outperforming baseline HyperGAT by 3.28%, and (ii) the full HyperGAT-BERT-RAS achieves 78.66% accuracy and 0.7806 F1-score, with RAS contributing the most to performance gains. These improvements suggest the potential for more reliable scoring of diverse student answers, reduced teacher grading burden, and enhanced feasibility of AI-assisted formative assessment in real classrooms, although empirical validation with teachers and students is needed.

Schlagwörter

Stichwörter der Autor:innen

BERTSiamese neural networkautomated short-answer gradinghypergraph attention networkreference answer set

Autor:innen und Institutionen

  • Zhejiang Philosophy and Social Science Laboratory for the Mental Health and Crisis Intervention of Children and Adolescents, Zhejiang Normal University, Jinhua 321004, China.

ORCID-Profile: Sheng Su, Chunhua Kang

Förderung

  • Humanities and Social Sciences Fund of the Ministry of Education
  • Zhejiang Philosophy and Social Science Laboratory for the Mental Health and Crisis Intervention of Children and Adolescents

Zitieren

APA

Liu, C., Wan, X., Ni, Z., Su, S., & Kang, C. (2026). BERT-Enhanced HyperGAT with Siamese Networks and Reference Answer Set for Automated Short-Answer Scoring. Behavioral Sciences, 16(6), 946. https://doi.org/10.3390/bs16060946

Vancouver

Liu C, Wan X, Ni Z, Su S, Kang C. BERT-Enhanced HyperGAT with Siamese Networks and Reference Answer Set for Automated Short-Answer Scoring. Behavioral Sciences. 2026;16(6):946. doi:10.3390/bs16060946

BibTeX
@article{Liu2026,
  author = {Liu, Chen and Wan, Xiaofen and Ni, Zhihao and Su, Sheng and Kang, Chunhua},
  title = {BERT-Enhanced HyperGAT with Siamese Networks and Reference Answer Set for Automated Short-Answer Scoring},
  journal = {Behavioral Sciences},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {946},
  doi = {10.3390/bs16060946}
}
Kostenlos starten →