Development of a Deep Learning-Based Green-Constitution Digital Education Platform as an Effort to Enhance Environmental Literacy in Educational Institutions

Abstract

Environmental pollution remains a significant challenge in Indonesia, including in Sigi Regency, Central Sulawesi, where high volumes of daily waste are compounded by limited waste-management capacity. Existing structural interventions, such as waste banks and local regulations, have not been sufficient to address this problem, highlighting the need for educational innovations that strengthen environmental literacy among younger generations. This study developed Green-Constitution, an Android-based digital learning platform designed to promote students’ environmental literacy through an interactive learning environment. The platform was developed using Flutter for the frontend and Firebase for the backend, supporting user authentication, data management, quizzes, task submission, and participatory environmental issue mapping. The platform was evaluated with 200 students from two schools using a pre-test–post-test design, while user satisfaction was assessed using eight indicators. Differences between pre-test and post-test scores were analyzed using the Wilcoxon Signed-Rank Test. The results revealed a statistically significant improvement in students’ scores after using the platform (Z = −9.795, p < 0.05), indicating enhanced environmental literacy. User satisfaction was also rated as Excellent, with particularly positive evaluations of language clarity, student–teacher collaboration, interactivity, and ease of use. These findings demonstrate that the Green-Constitution platform can serve as an effective digital learning medium for strengthening students’ conceptual understanding and environmental awareness. Future development should focus on improving accessibility, contextual visual content, and interactive features to further support sustainable environmental literacy.