AI-based Feedback for Reflective Writing for Higher Secondary Education to Improve Metacognition
AI-based feedback to support students in higher secondary education in their reflective writing skills to improve metacognition.
Duration: April 2026 – September 2026
Status: Ongoing
Educational Level: Upper Secondary Level
Topic: Artificial Intelligence AI
Keywords: AI, Reflective Writing, Metacognition
Initial Situation
Providing high-quality, personalised feedback is important to develop reflective writing skills. Effective and timely feedback is essential for students to evaluate and craft coherent, personal, and deep reflective texts. However, providing personal feedback on reflective writing to students and how to improve reflective texts, especially in large class sizes, pose a significant challenge to teachers to support students in developing effective reflective writing skills.
Objectives
We aim to address this gap by designing, developing and evaluating a novel AI-based adaptive feedback system for students in higher secondary education in Switzerland that provides learning oriented, adaptive and targeted feedback to improve reflective writing skills. The system leverages recent advances in large language models (LLMs) and generative AI, provides specific and targeted feedback in reflective text for improvement, and fosters actionability of feedback in reflective writing
Method
We will use a mixed-methods design with a design science research approach. First, we will conduct interviews with teachers and review literature on AI-based reflective writing. Then, we will identify how AI-feedback can support reflective writing and determine which feedback functions are most useful. Additionally, we will conduct an empirical study in higher secondary education in Switzerland, incorporating Rflect into regular classes. We will collect quantitative and qualitative data to derive initial design requirements and answer our research question.
Planned Translation
From the beginning, teachers and students are co-designers of our application. We integrate Rflect into actual classes in Swiss schools. To ensure the outcomes are immediately usable, we will provide a teacher-ready implementation guide and a reusable constructive-alignment framework linking learning goals and activities.
The project will provide evaluated design principles for AI-based feedback in reflective writing for adolescents in Switzerland. To ensure our project’s relevance, we will conduct an empirical study in upper secondary level classes using Rflect during regular classes. Our goal is to collect quantitative data based on learning analytics and additionally, we will collect qualitative data to capture perceptions, usability, and contextual factors that influence adoption.
