When AI simulates teaching personas: Linguistic dimensions of LLM-generated classroom discourse
PLOS One · 06.11.2026 · 21 (11) · e0360650
DOI: 10.1371/journal.pone.0360650 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.11.2026. Verfasst von Tony Berber Sardinha und 1 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in Applied Linguistics and Language Studies (LAEL) & Graduate Program in Social Psychology (PSO)/Pontifical Catholic University of S…. Hauptthemen laut MEDLINE: Teaching, Linguistics. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação de Amparo à Pesquisa do Estado de São Paulo, Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
This study investigates how GPT-4o constructs the social role of teacher through discourse and how this discourse compares with naturally occurring classroom teaching. We generated 19,950 AI classroom teaching texts from a corpus of online college teaching using 56 teacher personas plus a baseline condition. The AI-generated texts contained the original student turns alongside the AI-teacher turns. We analyzed the resulting corpus using Lexical Multi-Dimensional Analysis (LMDA), a bottom-up corpus-linguistic method that identifies dimensions of discourse variation from recurrent patterns of lexical covariation. Five dimensions emerged: Macro-Structuring Discourse vs. Performative Stagecraft, L1-scaffolded Guidance vs. Provocative Challenge, Procedural Control vs. Rapport-driven Engagement, Evaluative Control vs. Reflective Aesthetic Engagement, and Informal Facilitation vs. Formal Deductive Exposition. Comparison with the corresponding human classroom discourse showed that GPT-4o frequently magnified teaching discourses already present in human interaction, particularly organizational, procedural, and expository discourse. It also introduced more artificial forms of teaching discourse characterized by theatrical performance, confrontation, and evaluative pressure. Mixed-effects analyses showed significant differences between human and AI discourse on all five dimensions. Persona prompting also affected dimension scores, but differentiation among the 57 conditions was uneven: many personas occupied overlapping positions, and differences occurred on only some dimensions. The findings show that GPT-4o can produce distinct forms of teaching discourse, yet many different persona prompts repeat similar discourses, suggesting a saturation point beyond which the LLM cannot yield new teaching discourses. More generally, the study demonstrates how corpus-based discourse analysis can characterize the forms of teaching that emerge when an LLM is instructed to perform a professional role.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Graduate Program in Applied Linguistics and Language Studies (LAEL) & Graduate Program in Social Psychology (PSO)/Pontifical Catholic University of Sao Paulo, Brazil.
- Sao Paulo State University at S. José do Rio Preto (UNESP-SJRP), Brazil.
ORCID-Profile: Marilisa Shimazumi
Förderung
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
Berber Sardinha, T., & Shimazumi, M. (2026). When AI simulates teaching personas: Linguistic dimensions of LLM-generated classroom discourse. PLOS One, 21(11), e0360650. https://doi.org/10.1371/journal.pone.0360650
Vancouver
Berber Sardinha T, Shimazumi M. When AI simulates teaching personas: Linguistic dimensions of LLM-generated classroom discourse. PLOS One. 2026;21(11):e0360650. doi:10.1371/journal.pone.0360650
BibTeX
@article{BerberSardinha2026,
author = {Berber Sardinha, Tony and Shimazumi, Marilisa},
title = {When AI simulates teaching personas: Linguistic dimensions of LLM-generated classroom discourse},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0360650},
doi = {10.1371/journal.pone.0360650}
}
EUVIMED