EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Revealing teaching quality through lesson semantics: A GPT ‐assisted analysis of transcripts

Richard Göllner iD, Rebecca Lazarides iD, Philipp Stark

British Journal of Educational Psychology · 2025

DOI: 10.1111/bjep.70001 ↗

At a glance

Journal article in British Journal of Educational Psychology, 2025. Written by Richard Göllner and 2 co-authors. Institution: Department of Education, University of Potsdam, Potsdam, Germany. Major MEDLINE topics: Semantics, Teaching, Mathematics, School Teachers. Cited 2 times so far (Crossref); 50 references. The full text is freely available (open access, CC BY 4.0).

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Existing conceptions of teaching quality assume that classroom interactions serve as the foundation for effective teaching. The resulting data necessitates analytical approaches capable of extracting the semantics of these interactions.

Aim

This study investigates whether and to what extent lesson semantics provide insights into teaching quality (i.e., cognitive engagement, encouragement and warmth, multiple approaches, and the nature of discourse). To achieve this, GPT‐4 was applied as a tool for analysing lesson transcripts. Sample The study is based on data from the TALIS Video study, which included N = 50 teachers delivering two consecutive mathematics lessons in 9th grade. Teaching quality was annotated by trained observers across multiple dimensions.

Method

The analysis involved embedding segmented lesson transcripts to examine their semantic characteristics and associations with human annotations of teaching quality. Additionally, we applied content‐informed prompting to evaluate the interpretability of semantic characteristics for the considered dimensions.

Results

GPT‐4 identified five distinct semantic representations of transcripts, varying at both the teacher and lesson levels. These representations were related to teaching quality, accounting for up to 20% of variance in teaching quality annotations. Content‐informed prompting aligned lesson segments more closely with semantic representations, supporting their interpretability.

Conclusion

The findings suggest that lesson semantics serve as indicators of teaching quality, offering a promising approach to understanding effective classroom learning.

Subjects

MeSH terms (MEDLINE)

SemanticsTeachingMathematicsSchool TeachersHumansFemaleMaleAdultChild

Author keywords

GPT‐4lesson transcriptsmathematics lessonsteaching quality

Authors and institutions

  • Department of Education, University of Potsdam, Potsdam, Germany.
  • Cluster of Excellence Science of Intelligence, Technical University Berlin, Berlin, Germany.
  • Hector Research Institute of Education Sciences and Psychology, University of Tübingen, Tübingen, Germany.

ORCID profiles: Richard Göllner, Rebecca Lazarides

Cite

APA

Göllner, R., Lazarides, R., & Stark, P. (2025). Revealing teaching quality through lesson semantics: A GPT ‐assisted analysis of transcripts. British Journal of Educational Psychology. https://doi.org/10.1111/bjep.70001

Vancouver

Göllner R, Lazarides R, Stark P. Revealing teaching quality through lesson semantics: A GPT ‐assisted analysis of transcripts. British Journal of Educational Psychology. 2025. doi:10.1111/bjep.70001

BibTeX
@article{Gllner2025,
  author = {Göllner, Richard and Lazarides, Rebecca and Stark, Philipp},
  title = {Revealing teaching quality through lesson semantics: A GPT ‐assisted analysis of transcripts},
  journal = {British Journal of Educational Psychology},
  year = {2025},
  doi = {10.1111/bjep.70001}
}
Start for free →