<![CDATA[Purpose – This study aims to determine the effect of implementing the Deep Learning-based PjBL model on students' learning interest in the fourth-grade science subject in elementary schools.Methods – This study employed a quantitative approach using a quasi-experimental method and a pretest-posttest control group design. The research sample consisted of 81 fourth-grade students from SDN Sunggapan and SDN Pasirgabig, comprising 33 students from Class 4A at SDN Sunggapan as the experimental group and 28 students from Class 4B at SDN Sunggapan along with 20 students from Class 4 at SDN Pasirgabig as the control group. The experimental class was taught using a Deep Learning-based PjBL model, while the control class used conventional teaching methods. Data were collected using a learning interest questionnaire and analyzed using normality tests, homogeneity tests, paired-sample t-tests, and independent-sample t-tests.Findings – The results of the study indicate that the implementation of a Deep Learning-based PjBL model has a significant effect on students’ interest in learning. The results of the Paired Sample T-Test for the experimental class showed a significance value of 0.004 < 0.05, while the Paired Sample T-Test for the control class showed a significance value of 0.045 < 0.05, while the results of the independent-samples T-Test also showed a significance value of 0.001 < 0.05, indicating a significant difference in learning interest between the experimental and control classes following the intervention.Research Implications – The findings indicate that integrating PjBL with a deep learning approach can be considered an alternative strategy for promoting students’ interest in learning IPAS. However, the study was limited by the non-random assignment of participants, unequal group sizes, and the involvement of students from different school contexts. Therefore, the findings should be interpreted within the context of participating in schools.]]>
Copyrights © 2026
