More Than AI: Developing Intelligent Chatbot to Empower Algebra Mastery for Grade VII Students
PRISMA · 04.06.2026 · 15 (1) · 1-9
DOI: 10.35194/jp.v15i1.5770 ↗Kurz gefasst
Fachartikel in der Zeitschrift PRISMA, online erschienen am 04.06.2026. Verfasst von Muhammad Nur Ramadhan und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
The challenge of learning algebra for junior high students necessitates innovative educational tools. This study aimed to develop and evaluate an intelligent chatbot, powered by a fine-tuned Mistral AI model, to empower algebra mastery for Grade VII students. R&D methodology using the ADDIE model was employed, involving one expert validator, 20 students, and 5 teachers for the evaluation. Data were collected through questionnaires and a post-test. The findings revealed that the chatbot was highly successful, achieving an expert validation score of 91.11% ("Very Valid") and a user practicality score of 84.42% ("Very Practical"). Furthermore, the chatbot was proven effective, as 84% of students achieved the classical mastery threshold on the post-test with a class mean score of 82.0. This research concluded that a specifically customized AI chatbot is a valid, practical, and effective medium for mathematics education.
Zitieren
APA
Ramadhan, M. N., Qohar, A., Sisworo, S., & Yasin, M. (2026). More Than AI: Developing Intelligent Chatbot to Empower Algebra Mastery for Grade VII Students. PRISMA, 15(1), 1-9. https://doi.org/10.35194/jp.v15i1.5770
Vancouver
Ramadhan MN, Qohar A, Sisworo S, Yasin M. More Than AI: Developing Intelligent Chatbot to Empower Algebra Mastery for Grade VII Students. PRISMA. 2026;15(1):1-9. doi:10.35194/jp.v15i1.5770
BibTeX
@article{Ramadhan2026,
author = {Ramadhan, Muhammad Nur and Qohar, Abd. and Sisworo, Sisworo and Yasin, Mohamad},
title = {More Than AI: Developing Intelligent Chatbot to Empower Algebra Mastery for Grade VII Students},
journal = {PRISMA},
year = {2026},
volume = {15},
number = {1},
pages = {1--9},
doi = {10.35194/jp.v15i1.5770}
}
EUVIMED