EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A transformer-based embedding approach to developing short-form psychological measures

Se-Jin Jung, Jang-Won Seo

Frontiers in Psychology · 13.08.2025 · 16

DOI: 10.3389/fpsyg.2025.1640864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychology, online erschienen am 13.08.2025. Verfasst von Se-Jin Jung und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, Jeonbuk National University, Jeonju, Republic of Korea. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jeonbuk National University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Developing short-form psychological measures is essential for reducing respondent burden, saving time, and conserving resources. However, existing short-form development approaches typically require full-scale administration and rely on factor analysis or machine learning techniques based on response data.

Methods

This study proposes a novel, data-independent method for item reduction using transformer-based semantic embeddings. Items from the International Personality Item Pool Big-Five Factor Markers (IPIP-50) were embedded using the sentence-t5-xxl model to generate dense semantic representations. These embeddings were clustered via K-means, and representative items were selected based on their proximity to cluster centroids.

Results

The resulting 30-item short form preserved the original five-factor structure and demonstrated strong psychometric properties. When compared with Classical Test Theory and a Genetic Algorithm, the proposed method achieved comparable levels of reliability, convergent validity, and predictive performance.

Discussion

These findings highlight the potential of transformer-based embedding approaches for efficient item reduction and item development. The results support the feasibility of a resource-efficient, linguistically grounded alternative to data-dependent reduction methods.

Schlagwörter

Stichwörter der Autor:innen

item reductionpsychological measuressemantic clusteringshort-form developmenttransformer-based embedding

Autor:innen und Institutionen

  • Department of Psychology, Jeonbuk National University, Jeonju, Republic of Korea.

Förderung

  • Jeonbuk National University

Zitieren

APA

Jung, S. J., & Seo, J. W. (2025). A transformer-based embedding approach to developing short-form psychological measures. Frontiers in Psychology, 16. https://doi.org/10.3389/fpsyg.2025.1640864

Vancouver

Jung SJ, Seo JW. A transformer-based embedding approach to developing short-form psychological measures. Frontiers in Psychology. 2025;16. doi:10.3389/fpsyg.2025.1640864

BibTeX
@article{Jung2025,
  author = {Jung, Se-Jin and Seo, Jang-Won},
  title = {A transformer-based embedding approach to developing short-form psychological measures},
  journal = {Frontiers in Psychology},
  year = {2025},
  volume = {16},
  doi = {10.3389/fpsyg.2025.1640864}
}
Kostenlos starten →