GPT4-coded sentiment of students' open-ended general feedback about the intervention was overwhelmingly positive¶
Claim · All claims
Evidence · 1 study · designr2·q1
Currency · newest study 2025 · 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.
q1 i? 92.9% of general-feedback responses were coded positively, 7.1% neutrally, and 0% negatively by GPT4. → Daniel M. Oppenheimer 2025
Evidence¶
Daniel M. Oppenheimer 2025¶
Daniel M. Oppenheimer, Trent N. Cash, Allison E. Connell Pensky. (2025). You've Got AI Friend in Me: LLMs as Collaborative Learning Partners. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00521-6
q1 · i? · design · r2
Sentiment analysis of open-ended survey responses conducted by ChatGPT4, which the authors note the literature supports for student feedback; results reinforce the Likert affective data. No effect size printed.
"92.9% of the responses were coded by GPT4 as positively valenced, 7.1% were coded as neutrally valenced, and 0% were coded as negatively valenced."
Discussion¶
Related Claims¶
- 90% of open-ended survey responses about the ChatGPT activity were neutral in sentiment, with 2% positive and 8% negative — reports the opposite
- Sentiment toward GenAI in the course was 86% positive overall, while ethical concerns generated 62% negative sentiment — related
- Participants' perceptions of AI in higher education shifted from 20% negative and 40% neutral pre-institute to 0% negative and 90% positive post-institute — related
- Human-LLM sentiment divergences were patterned: the LLM tended to assign affective labels to statements a human coder read as neutral — related
- Public sentiment toward AI in education on Twitter was predominantly positive (81.65% of tweets) across 2019–2024 — related
- GPT-generated tutor feedback is predominantly positive or neutral in sentiment — related
- Students engaged deeply with LLM feedback, with coded evidence of reflection, rebuttal, and acceptance in the large majority of responses — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
positive-sentiment-open-ended-feedback |
title |
GPT4-coded sentiment of students' open-ended general feedback about the intervention was overwhelmingly positive |
description |
GPT4-coded sentiment of students' open-ended general feedback about the intervention was overwhelmingly positive |
status |
review |
evidence_strength |
weak |
newest_evidence |
2025 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — daniel-m-oppenheimer-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.