Claim Missing Document
Check
Articles

Found 1 Documents
Search

Development of a Deep Learning-Based E-LKPD for Science and Social Studies (IPAS) on the Topic “My Region, My Pride” for Fifth-Grade Students Dwi Ajeng Safitri; Sulistyarini; Dede Suratman; Agung Hartono; Rini Muharini
Jurnal Penelitian Pendidikan IPA Vol 12 No 7 (2026)
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v12i7.15610

Abstract

Deep Learning is an educational approach that focuses on improving the quality of learning and students’ learning experiences. One of the learning strategies that integrates the Deep Learning approach is the use of technology, such as transforming printed student worksheets (LKPD) into electronic worksheets (E-LKPD). E-LKPDs not only contain direct-question tasks but can also be modified through gamification, which represents an integration of the Deep Learning approach. This study aimed to develop a feasible and effective Deep Learning-based E-LKPD to improve students’ learning outcomes in Science and Social Studies (IPAS). The research employed the ADDIE development model consisting of Analysis, Design, Development, Implementation, and Evaluation stages. The results indicated that all three E-LKPDs were highly feasible. E-LKPD 1 achieved feasibility scores of 92.9% (didactic aspect), 85% (construction aspect), and 80% (technical aspect). E-LKPD 2 obtained 91.4%, 85%, and 80%, respectively, while E-LKPD 3 achieved 90%, 84%, and 81.25%, respectively. The N-Gain test showed that all three E-LKPDs were moderately effective in improving students’ IPAS learning outcomes on the topic My Region, My Pride in Grade V of SDN 36 South Pontianak, with N-Gain scores of 62.8%, 62.3%, and 62.1%, respectively. Student responses were highly positive overall. The three E-LKPDs received very positive ratings in terms of appearance (84.5%–85.3%) and usefulness (85.8%–86.4%), while presentation aspects were rated positively (82.6%–83.8%). These findings suggest that Deep Learning-based E-LKPDs are feasible, effective, and well-received as learning media.