Artificial intelligence prediction model for educational knowledge representation through learning performance

Abstract

Precision education derives teaching and learning opportunities by customizing predictive rules in educational methods. Innovative educational research faces new challenges and affords state-of-the-art methods to trace knowledge between the teaching and learning ecosystem. Individual intelligence can only be captured through knowledge level representation, i.e., learning performance that sheds light on learners’ knowledge and ability to apply skills after course learning in the education process. Emerging Artificial Intelligence (AI) predicts future learning performance in the higher education system. This research aims to implement an AI application using a supervised learning model to predict students' learning abilities, which are developed by the end of course study. The authors examine learners' performance skills using Bloom's classifiers. This study aims to develop more innovative ways to represent learners’ knowledge level by implementing AI models in learning performance. This prediction model assists both teacher and learner in understanding learners' knowledge abilities, and this study can find out the current status of learners' knowledge.

Keywords

• learning outcome
• skill level
• blooms’ taxonomy
• artificial intelligence
• learning performance