Connect with us

November
23 – 25
Berlin

.

Presentation HIG110

Making Decisions with Learning Analytics from Heterogeneous Platforms by Using Ontology and Graph Database

Learning Analytics (LA) is primarily to improve learning efficiency and learning operation effectiveness, as well as providing educators, learners, administrators and policy makers with actionable insights to online course level activities. LA solutions should be able to integrate data coming from many different data sources (heterogeneous platforms). However, studies reported integrating LA that combine data of similar formats due to the limitation of relational database capability. Other studies used educational data specifications to enable a more uniform representation of learning activity data thus allowing the combination of data of the same standards.

However, a data model that integrates learning analytics is restricted and leave many data unusable. Another approach to the alignment of concepts would be to use an ontology. Ontology is a data model that represents knowledge as a set of concepts within a domain and relationship between these concepts. When using an ontology, it is possible to add descriptions and meaning to data coming from various sources, and to combine, support, and reuse different specifications.

Ontologies would be one of the best options to be used to integrate heterogeneous data sources. Ontologies have been used for creating an interoperable shared data model for heterogeneous healthcare and manufacturing systems. However, since ontology is a data model that represents knowledge as a set of concepts within a domain and relationship between these concepts, the ontology-based data integration model in a different domain is not reusable for another domain.

Therefore, in this session, an ontology-based data integration model is proposed for integrating learning analytics from heterogeneous platforms. The proposed data model is expected to give benefits to systems developers in data science and analytics for education systems. By involving heterogeneous platforms, the model contributes in improving the quality of education system.

Learning Outcomes

  • What is ontology?
  • How to design an ontology using a sample learning dataset
  • How to query an ontology based learning repository in a graph database

Speaker

OEB speaker Sazilah Salam

Sazilah Salam

Universiti Teknikal Malaysia Melaka, Malaysia