<![CDATA[Indonesian language learning assessment in elementary schools is generally still dominated by manual methods oriented towards final results, making the provision of formative feedback suboptimal. This study aims to develop and test the feasibility of the MUSSA (Mobile User Assistant for Smart School Assessment) web-based platform as an Artificial Intelligence (AI)-based digital assistant for assessing student essays. This study employs the Research and Development (R&D) method using the ADDIE model (Analysis, Design, Development, Implementation, Evaluation). The feasibility of the platform was evaluated by media and material experts, followed by a longitudinal field trial (six meetings) involving 74 5th-grade students and 3 teachers across three elementary schools in West Java. Expert validation results showed an average feasibility percentage of 86% (Highly Valid). In the implementation stage, the platform was deemed highly practical by teachers (87.2%) for reducing grading. Nevertheless, findings indicate that the AI feedback language (Natural Language Processing) needs to be refined to be more child-friendly.]]>
Copyrights © 2026
