aceModerate evidence
Published recordEducationGood Space
More
Exploring the effects of AI-powered feedback in language learning: a meta-analysis
- Truvace record
- TRV-2026-2751raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Systematic review or meta-analysis
- Sources
- 1 sourcePeer-reviewed
- sha256
- 3bf7092759a9…check it
Despite growing interest in artificial intelligence in education, the effectiveness of AI-generated feedback in language learning remains unclear. This meta-analysis examined its impact on language learning performance and affective outcomes. A systematic search of the Web of Science and EBSCO databases (2004–2024), supplemented by manual journal searches, identified 55 eligible studies. Results indicated significant positive effects on learning performance (g = 1.106, p < 0.001; k = 49) and affective outcomes (…
The gain
A meta-analysis of 55 studies found AI-generated feedback improved language learning performance (g = 1.106, 49 studies) and affective outcomes such as learner attitudes (g = 0.823, 16 studies).
Sources
1 on file- Educational Psychologydoi:10.1080/01443410.2026.2735272
Cite this record
v1Truvace Impact Record TRV-2026-2751, v1: “Exploring the effects of AI-powered feedback in language learning: a meta-analysis.” Truvace, 2026-11-12. /record/TRV-2026-2751 (accessed on the day you copy it). sha256 3bf7092759a91d0c…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2751 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.