Teacher- Versus AI-Generated (Poe Application) Corrective Feedback and Language Learners’ Writing Anxiety, Complexity, Fluency, and Accuracy
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This study examines the effects of corrective feedback (CF) on language learners’ writing anxiety, writing complexity, fluency, and accuracy, and compares the effectiveness of feedback from human teachers with an AI-driven application called Poe. The study included three intact classes, each with 25 language learners. Using a quasi-experimental design with pretest and posttest measures, one class received feedback from the teacher, one from the Poe application, and the third received no response to their writing. Data were generated though tests and a writing anxiety scale developed for the study. Data analysis, conducted using one-way ANOVA tests, revealed significant effects of teacher and AI-generated feedback on learners’ writing anxiety, accuracy, and fluency. Interestingly, the group that received AI-generated feedback performed better than the group that received teacher feedback or no AI support. Additionally, learners in the AI-generated feedback group experienced a more significant reduction in writing anxiety than their peers. These results highlight the remarkable impact of AI-generated CF on improving writing outcomes and alleviating anxiety in undergraduate language learners at East China University of Political Science and Law . The study demonstrates the benefits of integrating AI applications into language learning contexts, particularly by promoting a supportive environment for students to develop writing skills. Educators, researchers, and developers can use these findings to inform pedagogical practices and technological interventions to optimize the language learning experience in primary school settings. This research highlights the effectiveness of AI-driven applications in language teaching. It highlights the importance of considering learners’ psychological well-being, particularly anxiety levels, when developing effective language learning interventions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it