Perspectives on Using Automated Writing Evaluation Systems to Provide Written Corrective Feedback in the ESL Classroom
Bibliographic record
Abstract
While feedback is widely considered essential for second language (L2) writing development (Bitchener & Ferris, 2012), teachers may not always be able to provide their learners with immediate and frequent corrective feedback. Automated writing evaluation (AWE) systems can help respond to this challenge by providing L2 learners with written corrective feedback (WCF) instantaneously and as frequently as needed both inside and outside the ESL classroom. Proponents of the use of AWE systems argue that these systems can facilitate more writing practice, increase learner motivation and accuracy, and promote learner autonomy. Critics argue that AWE systems cannot give individualized feedback, are prone to errors, can diminish the role of the teacher, and warp students’ notions of good writing. As a compromise, it is recommended to use feedback from AWE systems to complement, rather than replace, teacher WCF. In this perspectives paper, we discuss the main benefits and drawbacks of using AWE to provide WCF in the ESL classroom. We conclude by arguing that, when used judiciously and effectively to complement teacher feedback, WCF from AWE systems can support teachers’ work and enhance learners’ writing motivation and development in the ESL classroom. Alors qu’un consensus existe pour dire que la rétroaction est essentielle pour le développement de la rédaction en langue seconde (L2) (Bitchener & Ferris, 2012), les enseignants ne sont peut-être pas toujours en mesure de fournir une rétroaction corrective immédiate et fréquente à leurs apprenants. Les systèmes d’évaluation automatique de rédaction peuvent aider à répondre à ce défi en fournissant aux apprenants de L2 une rétroaction corrective écrite instantanée et de façon aussi fréquente que nécessaire à la fois en classe et hors de la classe d’ALS. Les défenseurs de l’utilisation des systèmes disent que ces systèmes peuvent encourager la pratique de la rédaction, augmenter la motivation et la précision de l’apprenant et promouvoir l’autonomie de l’apprenant. Les critiques avancent que les systèmes d’évaluation automatique ne peuvent pas donner de rétroaction personnalisée, sont susceptibles de faire des erreurs, peuvent diminuer le rôle de l’enseignant et déformer la perception des étudiants quant à ce qui constitue une bonne rédaction. On recommande, comme compromis, d’utiliser la rétroaction des systèmes d’évaluation automatique comme un complément, plutôt que comme un remplacement de la rétroaction corrective écrite de l’enseignant. Dans cet article donnant des perspectives, nous discutons des principaux avantages et inconvénients de l’utilisation de l’évaluation automatique de rédaction pour fournir de la rétroaction corrective écrite dans la classe d’anglais langue seconde. Nous arrivons à la conclusion que, utilisée de manière judicieuse et efficace pour compléter la rétroaction de l’enseignant, la rétroaction corrective écrite issue des systèmes d’évaluation automatique de rédaction peut soutenir le travail des enseignants et augmenter la motivation et le développement de la rédaction des apprenants dans la classe d’ALS.
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 | 0.038 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.003 | 0.010 |
| Scholarly communication | 0.018 | 0.014 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.007 | 0.004 |
| Insufficient payload (model declined to judge) | 0.003 | 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".