Related Experiment Videos
A Dynamic Written Corrective Feedback Framework Integrating AI Agent Delivery for Structured and Iterative Essay
Yucheng Sheng1, Malini Ganapathy2, Yifang Gao3
1School of Primary Education, Shangrao Preschool Education College.
Journal of Visualized Experiments : Jove
|August 10, 2026
Summary
The STEP-DWCF-R framework, using AI feedback and a robotic agent, significantly improved IELTS writing scores for EFL learners compared to traditional feedback methods. This dynamic, iterative approach enhances coherence and cohesion.
Area of Science:
- Educational Technology
- Artificial Intelligence in Education
- Second Language Acquisition
Background:
- Automated writing feedback systems often provide static, limited revision support.
- Existing feedback mechanisms lack dynamic scaffolding for iterative improvement.
- The need for enhanced feedback systems in English as a Foreign Language (EFL) writing instruction is critical.
Purpose of the Study:
- To evaluate the efficacy of the STEP-DWCF-R framework for dynamic written corrective feedback.
- To compare the impact of the STEP-DWCF-R framework against traditional feedback methods on EFL learners' writing skills.
- To assess the role of AI-generated feedback, teacher moderation, and iterative delivery in improving writing proficiency.
Main Methods:
- A quasi-experimental trial involving 32 EFL learners over eight weeks.
- Randomization of participants into either the STEP-DWCF-R group or a traditional feedback group.
- Assessment of IELTS Task 2 essays using anonymized, randomized scoring by independent raters (ICC = 0.86-0.93).
Main Results:
- The STEP-DWCF-R group showed significantly greater gains in overall IELTS band score (Δ = 1.03 vs. 0.31).
- Improvements were observed across all four analytic dimensions, particularly in Coherence and Cohesion.
- Learners using STEP-DWCF-R completed an average of 2.26 revision rounds per task, with decreasing error counts.
Conclusions:
- The integrated STEP-DWCF-R framework enhances IELTS writing improvement more effectively than traditional single-round feedback.
- AI-generated feedback, teacher moderation, and iterative delivery via a robotic agent are key components of this enhanced framework.
- The study highlights practical applications for AI-enhanced dynamic feedback in EFL writing contexts.
Related Concept Videos
01:16Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
01:29Impression Management Techniques III: Aligning Actions
Aligning actions are communicative strategies individuals employ to maintain social harmony and preserve personal identity in the face of potential disruptions to social norms. These actions are particularly important in managing social impressions when one's behavior might be seen as inappropriate, incompetent, or morally questionable.Types of Aligning ActionsThe three principal types of aligning actions are disclaimers, accounts, and apologies.DisclaimersDisclaimers are preventive; they are...
01:43Proofreading
Synthesis of new DNA molecules starts when DNA polymerase links nucleotides together in a sequence that is complementary to the template DNA strand. DNA polymerase has a higher affinity for the correct base to ensure fidelity in DNA replication. The DNA polymerase furthermore proofreads during replication, using an exonuclease domain that cuts off incorrect nucleotides from the nascent DNA strand.Errors during Replication Are Corrected by the DNA Polymerase EnzymeGenomic DNA is synthesized in...