SimSE¶
Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
SimSE is a dataset of 1,135 simulated five-minute teaching sessions by pre-service teachers, annotated for metacognitive modeling components and collected through the TeachSim platform by Xu and colleagues.
Components¶
- SimSE dataset of simulated teaching sessions for pre-service teachers rated on metacognitive modeling components: The SimSE dataset was collected as part of TeachSim, "a teaching simulation platform for pre-service teachers," from Fall 2022 to Spring 2023. It contains 1,135 five-minute transcribed teaching sessions (teachers' talk only), each annotated with five metacognitive modeling components — Unpacking, Self-Instruction, Self-Regulation, Objective, and Ending — scored 1 to 3 by experts. The sessions focus on teaching metacognitive modeling while unpacking a word problem, a practice the authors describe as critical for supporting students with special needs in general math education. (Paiheng Xu et al. (2024))
Claims¶
- ChatGPT zero-shot relevance extraction for instruction-quality assessment retrieves mostly irrelevant utterances and overestimates instruction quality [+W]
- Fine-tuned PLMs measure high-inference teaching practices better when the variable requires less pedagogical expertise, matching human-rater agreement on lexical variables but degrading on inference-heavy ones [+W]
Related Products and Programmes¶
Key Sources¶
- Paiheng Xu, Jing Liu, Nathan Jones, Julie Cohen, and Wei Ai. (2024). The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). https://aclanthology.org/volumes/2024.naacl-long/
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
simse |
title |
SimSE |
description |
SimSE is a dataset of 1,135 simulated five-minute teaching sessions by pre-service teachers, annotated for metacognitive modeling components and collected through the TeachSim platform by Xu and colleagues. |
status |
review |
moved_from |
element/simse-metacognitive-modeling-dataset |
product_kind |
dataset |
generated |
by process:sweep-kinds on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — paiheng-xu-2024 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.