Sistem Pakar Inklusif: Diagnosis Kesulitan Belajar Siswa dengan Teori Dempster-Shafer

Abstrak

Learning difficulties are complex issues in education that require early diagnosis to support effective and inclusive learning. This study aims to develop a web-based expert system using the Dempster–Shafer theory to diagnose students’ learning difficulties more comprehensively than conventional approaches such as Certainty Factor or Fuzzy Logic. The Dempster–Shafer method was selected for its ability to manage data uncertainty and overlapping symptoms. The research employed a Research and Development (R&D) approach with the Waterfall model, involving the stages of requirement analysis, system design, implementation, and testing. Data were collected from 50 students at MAS Teladan Ujung Kubu through teacher observations, exam results, and questionnaires from both students and parents. The findings indicate that the developed system can identify various types of learning difficulties such as dyslexia, dyscalculia, dysgraphia, and ADHD as well as categorize them into mild, moderate, and severe levels. The system functioned effectively without errors based on black box testing results. These outcomes demonstrate that the Dempster–Shafer theory is effective in handling diagnostic uncertainty and producing multi-level, comprehensive evaluations. Furthermore, the system shows potential for integration with artificial intelligence to support adaptive learning and personalized interventions within inclusive e-learning environments.

Identifier

• DOI: https://doi.org/10.29408/edumatic.v9i3.32107
• OpenAlex: https://openalex.org/W7124769248