JOURNAL OF SCIENCE AND SOCIAL RESEARCH
Vol. 9 No. 3 (2026): June 2026

PENGEMBANGAN MEDIA PEMBELAJARAN MATEMATIKA ADAPTIF BERBASIS MACHINE LEARNING UNTUK MENINGKATKAN HASIL BELAJAR SISWA

Mustika Fitri Larasati Sibuea (Universitas Royal)
Muhammad Ardiansyah Sembiring (Universitas Royal)
Hokkop Efendi Hasibuan (Universitas Royal)



Article Info

Publish Date
30 Jun 2026

Abstract

Abstract: This study aims to develop an adaptive mathematics learning media based on machine learning and to examine its feasibility and effectiveness in improving student learning outcomes. The media was developed using the 4D research and development model (define, design, develop, disseminate). A Random Forest algorithm was employed to classify students' ability into three categories (low, medium, high) based on their exercise history, allowing the media to automatically adjust the difficulty level of the exercises. The trial subjects were eighth-grade junior high school students of Tamansiswa Sukadamai. Data were collected through a needs analysis questionnaire, expert validation sheets, a System Usability Scale (SUS) questionnaire, and pretest-posttest learning outcome tests. The results indicate that the media is feasible, practical, and effective in improving student learning outcomes, and that the developed model shows good classification accuracy. Keywords: adaptive learning media, machine learning, learning outcomes, mathematics, Random Forest   Abstrak: Penelitian ini bertujuan untuk mengembangkan media pembelajaran matematika adaptif berbasis machine learning serta menguji kelayakan dan efektivitasnya dalam meningkatkan hasil belajar siswa. Media dikembangkan menggunakan model penelitian dan pengembangan 4D (define, design, develop, disseminate). Algoritma Random Forest digunakan untuk mengklasifikasikan kemampuan siswa ke dalam tiga kategori (rendah, sedang, tinggi) berdasarkan riwayat pengerjaan soal, sehingga media dapat menyesuaikan tingkat kesulitan latihan secara otomatis. Subjek uji coba penelitian adalah siswa kelas VIII SMP Tamansiswa Sukadamai. Data dikumpulkan melalui angket analisis kebutuhan, lembar validasi ahli, angket System Usability Scale (SUS), serta tes hasil belajar (pretest dan posttest). Hasil penelitian menunjukkan bahwa media dinyatakan layak, praktis, dan efektif meningkatkan hasil belajar siswa, serta model yang dikembangkan menunjukkan akurasi klasifikasi yang baik. Kata kunci: media pembelajaran adaptif, machine learning, hasil belajar, matematika, Random Forest

Copyrights © 2026






Journal Info

Abbrev

JSSR

Publisher

Subject

Computer Science & IT Economics, Econometrics & Finance Education Social Sciences

Description

Journal of Science and Social Research is accepts research works from academicians in their respective expertise of studies. Journal of Science and Social Research is platform to disclose the research abilities and promote quality and excellence of young researchers and experienced thoughts towards ...