Stanford MOOC Posts¶
Product or Programme · All products and programmes
Evidence · no claims cited
Description¶
A corpus introduced by Liu et al. (2025) containing anonymized learner forum posts and matched replies from 11 Stanford University MOOCs, annotated for sentiment, confusion, urgency, post type, and course metadata.
Components¶
- Stanford MOOC Posts dataset of annotated learner forum posts: The Stanford MOOC Posts dataset is the corpus used to fine-tune the LLMs and train the sentiment classifier. It "comprises 29,604 anonymized learner forum posts from 11 public online courses offered by Stanford University, spanning three subjects: humanities, medicine, and education." Posts carry sentiment, confusion, and urgency ratings on a 1–7 scale from three human raters, post-type flags, and course-type metadata; preprocessing yielded 8,322 matched post-reply pairs used for fine-tuning and evaluation. (Liu et al. (2025))
Claims¶
Related Products and Programmes¶
- Labelled corpus of 4,217 discussion posts
- Dataset of 69 Qassim University PBL course offerings with coded forum interactions
Key Sources¶
- Liu, Z., Xing, W., Jiao, X., & Li, C. (2025). Exploring Fairness and Explainability in LLM-Generated Support for Online Learning Discussion Forums. Journal of Learning Analytics, 12(3), 8–33. https://doi.org/10.18608/jla.2025.8885
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
stanford-mooc-posts |
title |
Stanford MOOC Posts |
description |
A corpus introduced by Liu et al. |
status |
review |
moved_from |
element/stanford-mooc-posts-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 — liu-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.