Developing a scaffolding chatbot to enhance mathematical problem-solving skills in three-variable linear equation systems
Hardiana Tri Wulandari, Santi Irawati, Susiswo
Source record
Source: Crossref
Published: Aug 17, 2026
DOI: 10.58524/jasme.v6i3.1459
Open original source ↗Source abstract
Background: Although chatbots are increasingly used in mathematics education, many primarily deliver direct answers or explanations, offering limited scaffolding to guide students systematically through mathematical problem solving. Aims: This study aimed to develop and evaluate a scaffolding chatbot designed to enhance students’ mathematical problem-solving skills in Three-Variable Linear Equation Systems. Method: A research and development approach employing the ADDIE model was conducted with 23 eleventh-grade students. Data were collected through expert validation, teacher and student practicality questionnaires, and pretest–posttest mathematical problem-solving assessments. Data analysis included descriptive statistics, normalized gain (N-gain), the Wilcoxon Signed-Rank Test, and effect size. Results: The chatbot achieved 80.28% validity, while teacher and student practicality scores reached 82.50% and 86.16%, respectively. Students demonstrated moderate improvement (N-gain = 0.45), with a significant difference between pretest and posttest scores (Z = 3.939, p < .05) and a large effect size (r = 0.82). Conclusion: The developed scaffolding chatbot demonstrated strong validity and practicality and provided promising evidence for supporting mathematical problem-solving development through gradual guidance, prompts, and feedback rather than direct solutions.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.