Multi-Label Classification of Learning Objects Using Clustering Algorithms Based on Feature Selection
Meryem Amanea, Karima Aissaouib, Mohammed Berradaa
- aArtificial Intelligence, Data Science and Emergent Systems Laboratory, Sidi Mohammed Ben Abdellah University, Fez, Morocco
- bSmart ICT-ENSA Oujda-UMP
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
In the field of online learning, the development of learning objects (LOs) has increased. LOs promote reusing and referencing educational content in various learning environments. However, despite this progress, the lack of a conceptual model for sharing suitable LOs between learners makes multiple challenges. In this regard, multi-label classification plays a significant role to make high-quality LOs, which can be accessible and reusable. This article highlights a new way of using learning objects based on Multi-Label Classification (MLC) and clustering algorithms with feature selection techniques. It suggests a new system that makes the most suitable choice among many alternative sources based on the Sharable Content Object Reference Model (SCORM). The proposed algorithm has been tested on a real-world application dataset related to the data analysis service for the learning science community. The experimental results show that our algorithm outperforms the traditional approach and produces good results.
TL;DRThis article suggests a new system that makes the most suitable choice among many alternative sources based on the Sharable Content Object Reference Model (SCORM) and clustering algorithms with feature selection techniques based on Multi-Label Classification (MLC). (Semantic Scholar)