Revealing teaching quality through lesson semantics
A GPT-assisted analysis of transcripts
Bibliographic Data
| ID | 5262718 |
|---|---|
| Authors | Richard Göllner (0000-0002-9442-7616, Department of Education University of Potsdam Potsdam Germany, corresponding author), Rebecca Lazarides (0000-0003-0392-4981, Department of Education University of Potsdam Potsdam Germany), Philipp Stark (0000-0001-6529-1142, Hector Research Institute of Education Sciences and Psychology University of Tübingen Tübingen Germany) |
| Year | 2025 |
| Volume | 95 |
| Issue | S1 |
| Pages | S300-S315 |
| Publication date | 2025-09-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | British Journal of Educational Psychology (JOURNAL) |
| Journal identifiers | ISSN: 0007-0998 • E-ISSN: 2044-8279 |
| Publisher | Wiley (PUBLISHER • GB) |
| DOI | 10.1111/bjep.70001 |
| PMID | 40495397 |
| OpenAlex | W4411221500 |
| Language | EN |
| Citations received | 1 |
| References cited | 34 |
BackgroundExisting 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.AimThis 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.SampleThe 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.MethodThe 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.ResultsGPT-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.ConclusionThe findings suggest that lesson semantics serve as indicators of teaching quality, offering a promising approach to understanding effective classroom learning
Mathematics education · Physics · Programming language · Quality (philosophy) · Semantics (computer science) · Computer Science · Educational Theory and Curriculum Studies · Mathematics Education and Teaching Techniques · Psychology · Visual and Cognitive Learning Processes
The Language of Schooling
GPT-3
Qualities of classroom observation systems
Student and teacher ratings of instructional quality
Sentence-Bert
Teacher-Student Relationships and Engagement
Professional competence of teachers
ChatGPT for good? On opportunities and challenges of large language models for education
Machine and expert judgments of student perceptions of teaching behavior in secondary education
Student Evaluations Fast and Slow
Don’t blame the teacher? The need to account for classroom characteristics in evaluations of teaching quality
Warning students of the consequences of examination failure
Explorations of classroom talk and links to reading achievement in upper elementary classrooms
Motivational messages from teachers before exams
Conceptualization, Measurement, and Improvement of Classroom Processes
No words'-Machine-learning classified nonverbal immediacy and its role in connecting teacher self-efficacy with perceived teaching and student interest
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2025 - 2025 (1) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 1 |