The Effectiveness of Using ChatGPT in Mathematics Learning at The Junior High School Level: A Systematic Literature Review

Abstract

The development of artificial intelligence (AI) has opened up new opportunities in education, one of which is through the use of ChatGPT as a learning aid. This study aims to systematically analyze the effectiveness of using ChatGPT in mathematics learning at the junior high school level based on a review of published literature. The method used is a Systematic Literature Review (SLR) by adopting the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol. The literature search was conducted in the Google Scholar, ERIC, Scopus, and ResearchGate databases with a publication range of 2022–2024. Of the 247 articles found, 28 articles met the inclusion criteria and were analyzed in depth. The results of the study indicate that: (1) ChatGPT has the potential to support junior high school mathematics learning, particularly in conceptual understanding, problem solving, and learning engagement, although the direction and magnitude of reported effects vary depending on instructional design, teacher guidance, and students’ digital literacy; (2) the metacognitive dimension remains the least explored despite showing strong potential; and (3) ChatGPT’s effectiveness is strongly influenced by the digital literacy of both teachers and students. The novelty of this research lies in the development of a framework for ChatGPT effectiveness indicators consisting of four dimensions: cognitive, affective, metacognitive, and pedagogical, which has not been found in previous studies. This research recommends the structured integration of ChatGPT into the junior high school mathematics curriculum with adequate teacher guidance.