Integrating and retrieving learning analytics data from heterogeneous platforms using ontology alignment: Graph-based approach
Mohd Hafizan Musa,
Sazilah Salam,
Siti Feirusz Ahmad Fesol,
Muhammad Syahmie Shabarudin,
Jack Febrian Rusdi,
Mohd Adili Norasikin,
Ibrahim Ahmad
Affiliations
Mohd Hafizan Musa
Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, 76100 Melaka, Malaysia; College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Cawangan Johor, Johor, Malaysia
Sazilah Salam
Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, 76100 Melaka, Malaysia; Web Science Institute, School of Electronics and Computer Science, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, UK; Corresponding author.
Siti Feirusz Ahmad Fesol
College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Cawangan Melaka, Melaka, Malaysia
Muhammad Syahmie Shabarudin
Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, 76100 Melaka, Malaysia
Jack Febrian Rusdi
Program Studi Teknik Informatika, Universitas Teknologi Bandung, Bandung, Indonesia
Mohd Adili Norasikin
Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, 76100 Melaka, Malaysia
Ibrahim Ahmad
Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka, 76100 Melaka, Malaysia
This study explores the possibility of integrating and retrieving heterogenous data across platforms by using ontology graph databases to enhance educational insights and enabling advanced data-driven decision-making. Motivated by some of the well-known universities and other Higher Education Institutions ontology, this study improvises the existing entities and introduces new entities in order to tackle a new topic identified from the preliminary interview conducted in the study to cover the study objective. The paper also proposes an innovative ontology, referred to as Student Performance and Course, to enhance resource management and evaluation mechanisms on course, students, and MOOC performance by the faculty. The model solves the issues of data accumulation and their heterogeneity, including the problem of having data in different formats and various semantic similarities, and is suitable for processing large amounts of data in terms of scalability. Thus, it also offers a way to confirm the process of data retrieval that is based on performance assessment with the help of an evaluation matrix.
