DIGITAL LIBRARY
A DATA MODEL FOR LEARNING ANALYTICS IN MOODLE
RWTH Aachen University (GERMANY)
About this paper:
Appears in: EDULEARN17 Proceedings
Publication year: 2017
Pages: 2402-2408
ISBN: 978-84-697-3777-4
ISSN: 2340-1117
doi: 10.21125/edulearn.2017.1498
Conference name: 9th International Conference on Education and New Learning Technologies
Dates: 3-5 July, 2017
Location: Barcelona, Spain
Abstract:
Virtual learning environments are widely used as they simplify and improve the teaching and learning processes. As part of the research project AIX - Future teaching & learning, we want to develop a learning analytics application to evaluate the generated logging data of our learning environment Moodle. The application needs to provide comprehensive statistics and reports to support the teaching and learning processes. The application will allow a variety of complex research questions to be answered which help the lecturers to improve the learning process. Moodle itself offers basic learning analytics functionality, but the logs allow a more detailed analysis of how learners and teachers use the system.

In this paper, we present how Moodle stores its logging data and explain why the existing data model is not well suited for learning analytics purposes. Therefore, we introduce our own data model and explain how the Moodle logging data can be converted into our format. In addition, we extend the database structure to allow the storing of arbitrary data which can be linked to learners and classes. This flexibility allows storing data from systems other than Moodle, which makes it possible to use meta data like exam grades for learning analytics. We claim that the presented model is well suited for storing the logging data of virtual learning environments and that it provides a good basis for a learning analytics application.

Keywords:
Learning analytics, moodle, VLE.