Partisan language is only weakly predictive of ideology in MOOC forum posts, suggesting linguistic convergence¶
Claim · All claims
Evidence · 1 study · associationalr2·q2
Currency · newest study 2018 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? A LASSO language classifier predicted ideology only weakly, with the relationship stronger in American Government than Saving Schools. → Yeomans 2018
Evidence¶
Yeomans 2018¶
Yeomans, M., Stewart, B. M., Mavon, K., Kindel, A., Tingley, D., & Reich, J. (2018). The Civic Mission of MOOCs: Engagement across Political Differences in Online Forums. International Journal of Artificial Intelligence in Education, 28, 553–589. https://doi.org/10.1007/s40593-017-0161-0
q2 · i? · associational · r2
Supervised learning analysis using penalized linear regression (LASSO, glmnet) with nested ten-fold cross-validation on 4,516 and 5,452 posts. Predicted-actual partisanship correlation "is not especially strong": rτ = .179 in American Government and rτ = .077 in Saving Schools, both p < .001.
"However the relation- ship between predicted and actual partisanship is not especially strong. Additionally, it seems to be somewhat stronger in American Government (r τ = .179, z(5452) = 19, p < .001), while it is weaker in Saving Schools (r τ = .077, z(4516) = 7.7, p < .001)."
Discussion¶
Related Claims¶
- Political ideology shows essentially no relationship with total forum activity in politically-themed MOOCs — related
- Forum comments show little evidence of ideology-based sorting, indicating engagement across political difference — related
- Politically-themed MOOCs attract U.S. students representing a diverse range of political beliefs across the ideological spectrum — related
- Structural topic models show partisan differences in topic use amount to less than 2% of all MOOC forum posts — related
- Upvote assortativity by ideology appeared in American Government but not Saving Schools, with sorting stronger among conservatives — related
- Course-created forum threads in these MOOCs showed balanced ideological contribution, with only small conservative-leaning exceptions — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
weak-partisan-language-distinctiveness |
title |
Partisan language is only weakly predictive of ideology in MOOC forum posts, suggesting linguistic convergence |
description |
Partisan language is only weakly predictive of ideology in MOOC forum posts, suggesting linguistic convergence |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2018 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yeomans-2018 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.