A GAI-Based Chatbot for Scaffolding Self-Regulated Learning - Insights from a Design-Based Research Approach

Oct 17, 2026

Uploaded by Jake

Generative AI is increasingly used in education through chatbots that support students without direct human intervention. While these tools can act as personalized learning companions, they may also drive overreliance, reduce creativity, and weaken critical thinking. The study strengthens students’ metacognitive and self-reflection processes by presenting a GAI-based chatbot designed through iterative cycles with 276 students across 10 courses. Findings highlight dialogic competence, personalization, and educator involvement to ensure effective AI-mediated reflection, positioning chatbots as collaborative agents that complement—not replace—teachers and learners.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Abstract

Introduction

Generative AI and learning analytics opportunities

Chatbots for student support without direct human intervention

Ethical use and pedagogical intent

Effects on writing, metacognition, and learning outcomes

Volume 13(1), 74–88 . [https://doi.org/10.18608/jla.2026.9143](https://doi.org/10.18608/jla.2026.9143) A GAI-Based Chatbot for Scaffolding Self-Regulated Learning: Insights from a Design-Based Research Approach Isabel Hilliger 1 , Mar Pérez-Sanagustín2 , Carlos González3 , Esteban Villalobos4 and Sergio Celis5 Abstract Generative AI (GAI) is increasingly integrated into education, particularly through chatbots that support students without direct human intervention. While these tools show promise as personalized learning companions, concerns persist about their potential to foster overreliance, limit creativity, and hinder the development of critical thinking. These risks highlight the need to strengthen students’ metacognitive skills and promote structured self-reflection. This paper presents the design and iterative development of a GAI-based chatbot aimed at scaffolding self-regulated learning. Through three design cycles involving 276 students in 10 courses, the chatbot evolved from a static assistant into a dynamic, course-integrated tool capable of supporting personalized, Socratic-style dialogue. Thematic analysis of diverse qualitative data sources revealed that students seek scaffolded support , such as human tutoring, and require explicit guidance to engage meaningfully with AI. Findings emphasize the importance of dialogic competence, personalization, and educator involvement in shaping effective AI-mediated reflection. This study underscores the need for pedagogically grounded AI tools that position chatbots as collaborative agents, complementing rather than replacing the roles of teachers and learners. It advocates for reflective teaching practices that clearly define the responsibilities of students, educators, and AI systems to ensure that GAI enhances deep learning and independent thought. | Notes for Practice
• Educational chatbots should be designed to foster reflective dialogue through Socratic-style prompts, as this approach encourages deeper learning and reduces student overreliance on automated answers.
• This study employed a design-based research approach to iteratively develop and refine a GAI-based chatbot, capturing lessons learned from real-world classroom use.
• GAI-based chatbots can be most effective when thoughtfully integrated into course design, supported by instructor guidance, and well aligned with learning activities. | | --- | | Keywords: Higher education , learning analytics , generative AI , design-based research, self-reflection
Submitted: 12/06/2025 —Accepted: 01/02/2026 — Published: 15/03/2026 | Corresponding author 1Email: [ihillige@uc.c](ihillige@uc.cl)[l](ihillige@uc.cl) Address: Pontificia Universidad Católica de Chile, Campus San Joaquín, Av. Vicuña Mackenna 4860, Macul, Santiago, Chile. ORCID iD. [https://orcid.org/0000-0001-5270-7655](https://orcid.org/0000-0001-5270-7655) 2Email: [mar.perez-sanagustin@irit.f](mar.perez-sanagustin@irit.fr)[r](mar.perez-sanagustin@irit.fr) Address: IRIT, Université Toulouse III – Paul Sabatier, 118 route de Narbonne 31062, Toulouse, France. ORCID iD: [https://orcid.org/0000-0001-9854-9963](https://orcid.org/0000-0001-9854-9963) 3Email: [cgonzalu@uc.c](cgonzalu@uc.cl)[l](cgonzalu@uc.cl) Address: Pontificia Universidad Católica de Chile, Campus San Joaquín, Av. Vicuña Mackenna 4860, Macul, Santiago, Chile. ORCID iD: [https://orcid.org/0000-0002-3154-0777](https://orcid.org/0000-0002-3154-0777) 4Email: [egvillalobos95@gmail.com](egvillalobos95@gmail.com) Address: IRIT, Université Toulouse III – Paul Sabatier, 118 route de Narbonne 31062, Toulouse, France. ORCID iD: [https://orcid.org/0000-0002-6026-3756](https://orcid.org/0000-0002-6026-3756) 5Email: scelis@uchile.cl Address: Universidad de Chile, Av. Beauchef 851, Santiago, Chile. ORCID iD: [https://orcid.org/0000-0002-0502-5608](https://orcid.org/0000-0002-0502-5608) 1. Introduction The convergence of artificial intelligence (AI) and learning analytics (L

FAQs

What problem does the paper address regarding educational chatbots?

It addresses concerns that generative-AI chatbots may lead to student overreliance, limit creativity, and hinder critical thinking. The paper argues for strengthening metacognitive skills and structured self-reflection.

How was the GAI-based chatbot developed in the study?

The chatbot was designed and iteratively improved through three design cycles. The process involved 276 students across 10 courses.

What capabilities did the chatbot gain across the design cycles?

It evolved from a static assistant into a dynamic tool integrated into courses, supporting personalized Socratic-style dialogue and scaffolded guidance.

What roles does the paper emphasize for educators and students?

The findings emphasize educator involvement and dialogic competence. The paper advocates clear responsibilities for students, educators, and AI systems so chatbots enhance deep learning and independent thought.

Oct 17, 2026

Uploaded by Jake