L’utilisation de ChatGPT 3.5 pour la rétroaction corrective écrite interactive en enseignement-apprentissage du français langue seconde : une étude exploratoire
Bibliographic record
Abstract
Generative artificial intelligence (GenAI) tools are becoming increasingly accessible, which makes it imperative to critically examine their potential impact in the educational environment, as well as the ways in which they can be integrated to enable learners to benefit from them. ChatGPT (OpenAI, 2022) is a conversational GenAI tool with which users can interact. The interactive nature of this tool seems to suggest affordances in language teaching and learning, specifically for textual revision. This exploratory study focuses on the use of ChatGPT for interactive written corrective feedback (WCF) in French as a second language. Participants (n=22) were French as a second language learners in a second-year university course. They first answered a questionnaire about their self-corrective practices for French writing tasks. Then, during a one-off intervention, they interacted with ChatGPT to solicit interactive WCF during synchronous exchanges. Finally, the participants answered a questionnaire about this experience and their perceptions of AI. A taxonomic analysis (Bilmes, 2009) within the framework of a qualitative content analysis (Selvi, 2019) was undertaken to develop typologies to classify the messages in the collected discussion threads. The quality of ChatGPT’s responses was also analyzed. The results show that many different types of prompts were created, but there were discrepancies in the degree of participant engagement. That said, the vast majority of participants claim to have benefited from this experience. ChatGPT’s responses were largely correct and appropriate, but the quality of the prompt was found to affect the quality of the response it solicits. The results of this study seem to demonstrate that ChatGPT could be a useful tool for interactive WCF in French language learning, however, more research is needed.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".