EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring

Wei Xia, Jin Wu iD, Jiarui Yu, Chanjin Zheng iD

Behavioral Sciences · 06.04.2026 · 16 (4) · 542

DOI: 10.3390/bs16040542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Behavioral Sciences, online erschienen am 06.04.2026. Verfasst von Wei Xia und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Educational Psychology, Faculty of Education, East China Normal University, Shanghai 200062, China. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Automated Essay Scoring (AES) systems confront two fundamental challenges: opaque “black-box” decision-making that limits educator trust, and insufficient validation across linguistically diverse educational contexts. This study proposes IRT-AESF, an innovative framework that bridges educational measurement theory and artificial intelligence by integrating item response theory (IRT) with deep learning. The framework generates three theoretically grounded psychometric parameters: student ability, item difficulty, and item discrimination, which provide transparent and interpretable explanations for scoring decisions. We rigorously evaluated IRT-AESF through 5-fold cross-validation on three large-scale datasets comprising 41,328 authentic essays from English and Chinese educational settings, including both classroom assessments and high-stakes examinations. Results demonstrate statistically significant improvements over competitive baseline models, achieving an 8.4% relative increase in quadratic weighted kappa while maintaining robust cross-lingual performance. This research advances the development of transparent, trustworthy automated assessment systems that deliver not only scores but meaningful diagnostic insights for educational practice.

Schlagwörter

Stichwörter der Autor:innen

Automated Essay ScoringBidirectional Encoder Representations from TransformersGeneralized Partial Credit ModelItem Response Theory

Autor:innen und Institutionen

  • Department of Educational Psychology, Faculty of Education, East China Normal University, Shanghai 200062, China.
  • Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai 200062, China.
  • School of Computer Science and Technology, Faculty of Information, East China Normal University, Shanghai 200062, China.

ORCID-Profile: Jin Wu, Chanjin Zheng

Zitieren

APA

Xia, W., Wu, J., Yu, J., & Zheng, C. (2026). The Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring. Behavioral Sciences, 16(4), 542. https://doi.org/10.3390/bs16040542

Vancouver

Xia W, Wu J, Yu J, Zheng C. The Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring. Behavioral Sciences. 2026;16(4):542. doi:10.3390/bs16040542

BibTeX
@article{Xia2026,
  author = {Xia, Wei and Wu, Jin and Yu, Jiarui and Zheng, Chanjin},
  title = {The Best of Two Worlds: IRT-Enhanced Automated Essay Interpretable Scoring},
  journal = {Behavioral Sciences},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {542},
  doi = {10.3390/bs16040542}
}
Kostenlos starten →