Aulyanissa Tsaqifa Maharshall
Universitas Sultan Ageng Tirtayasa

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

From Surface to Deep: Pembelajaran Berbasis Deep Learning dan Pjbl Untuk Penguatan Kemampuan Pemecahan Masalah Matematis Aulyanissa Tsaqifa Maharshall; Hepsi Nindiasari
FIBONACCI: Jurnal Pendidikan Matematika dan Matematika Vol. 11 No. 2 (2025): FIBONACCI: Jurnal Pendidikan Matematika dan Matematika
Publisher : Fakultas Ilmu Pendidikan Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/fbc.11.2.179-192

Abstract

This study aims to examine the indications of an increase in students' mathematical problem-solving abilities through the application of a Project-Based Learning (PjBL) model based on a Deep Learning approach. The background of this study is based on the condition of mathematics learning at SMP Negeri 1 Bayah, which is still dominated by a one-way method and is not yet optimal in facilitating active student involvement in problem solving. This study used a quasi-experimental method with a one-group pretest-posttest design involving 30 students in class VII-F. The research instrument was a descriptive test of mathematical problem-solving skills compiled based on Polya's steps. Data analysis included normality tests, Paired Sample T-Test, and N-Gain calculations to see the level of improvement in student abilities. The results of the analysis showed that there was a difference in scores between the pretest and posttest, and the average N-Gain value was 0.4, which was in the moderate category. These findings indicate an increase in students' mathematical problem-solving skills after the implementation of Deep Learning-based PjBL learning. However, given the research design that did not involve a control group, the results of this study are understood as preliminary (tentative) evidence regarding the potential of the applied learning. This study implies that the integration of PjBL and the Deep Learning approach has the potential to create more meaningful and contextual mathematics learning, and can serve as a basis for further research with a stronger experimental design.