metacognition
Filtering by topic metacognition(1)Clear all filters
- PaperLanguage Learning & Technology29 Jun 2026
Generative AI, visual scaffolds, and metacognition in EFL writing
Mei-Rong Alice Chen
A study proposes a Generative AI-assisted Visually Guided Progressive (GAI-VGP) writing approach integrating step-by-step visual scaffolds with interactive AI feedback. In a quasi-experiment with 58 EFL university students, the GAI-VGP group outperformed the control in writing performance, planning and evaluation strategies, and reflective awareness, though critical reflection remained limited and monitoring showed no gains due to learners outsourcing regulation to AI.
Original abstract
Fostering metacognitive awareness and reflective thinking remains a challenge in English as a Foreign Language (EFL) writing instruction. These cognitive processes are essential for enabling learners to monitor, evaluate, and engage in meaningful self-reflection throughout the writing cycle. Using Flower and Hayes’s cognitive process model and Jasper’s Experience-Reflection-Action framework, this study proposes a Generative AI-assisted Visually Guided Progressive (GAI-VGP) writing approach. This pedagogical design integrates step-by-step visual scaffolds with interactive AI feedback to foreground learner agency and promote reflective engagement. To evaluate this approach, a semester-long quasi-experimental study was conducted with 58 EFL university students. Data sources included pre- and post-writing tests, metacognitive awareness questionnaires, reflective thinking scales, AI chat logs, and reflection notes. The results showed that the GAI-VGP group significantly outperformed the conventional VGP group in writing performance, planning and evaluation strategies, and reflective awareness. Qualitative analyses indicated increased engagement in understanding and reflectively evaluating writing strategies, although critical reflection remained limited across both groups. Although AI significantly enhanced planning and evaluation, monitoring showed no significant gains, with prompt-log evidence revealing a displacement pattern in which learners outsourced real-time regulation to AI validation.