National Research Council of Italy (ITALY)
About this paper:
Appears in: EDULEARN19 Proceedings
Publication year: 2019
Pages: 7787-7793
ISBN: 978-84-09-12031-4
ISSN: 2340-1117
doi: 10.21125/edulearn.2019.1884
Conference name: 11th International Conference on Education and New Learning Technologies
Dates: 1-3 July, 2019
Location: Palma, Spain
The huge amount of traces left by students when using online learning platforms has paved the way to the development of new research fields. Educational Data Mining first, and Learning Analytics few years later, represent two major research areas that use data to obtain new insights on learning processes.

Kumar and Vijayalakshmi (2009) define Educational Data Mining (EDM) as “An emerging discipline concerned with developing methods for exploring the unique types of data that come from educational settings and using those methods to better understand students, and the settings which they learn in”. Learning Analytics (LA) is “the measurement, collection, analysis and reporting of data about learners and their contexts for purposes of understanding and optimizing learning and the environments in which it occurs”.

Definitions of EDM and LA suggest that they share the same general goal to support education “by improving the assessment, how problems in education are understood and how intervention are planned and selected” (Siemens and Baker, 2012). At a lower logical level, data analysis methods in EDM are increasingly influencing Learning Analytics techniques. Even though differences between EDM and LA exist, as reported by Siemens and Baker (2012), to the aim of this paper we focus on Learning Analytics, but keeping the Educational Data Mining as a source of data analysis techniques and models to feed Learning Analytics approaches.

A particularly rich area for future research in Learning Analytics is Open Learning Analytics (OLA) [13]. In general, OLA encompasses different stakeholders associated through a common interest in LA but with diverse needs and objectives, a wide range of data coming from various learning environments and contexts, as well as multiple infrastructures and methods that enable to draw value from data in order to gain insight into learning processes.

However, at present implementations of LA rely on a predefined set of indicators (Muslim, et a. 2017), and most of the tools used to analyse learning traces are focused on a specific aspect thus lacking in flexibility to provide multiple analysis. In this perspective, LA tools must be more flexible in order to support personalized LA approaches in which indicators are defined by users, thus enabling self-reflections in the definition of goals and research questions to be addressed.

In this paper we present a workflow management tool aimed at supporting the development of Open Learning Analytics applications specifically designed to deal with students’ interactions in online learning management systems.

The objectives of this platform are:
- Linking data made available from different source to facilitate the development of applications and services learner oriented;
- Providing a flexible tool to define personalized Learning Analytics approaches;
- Supporting the creation of Learning Analytics models, according to user self-defined goals and research questions.
- Supporting actors with different roles that can work collaboratively in the design of the elaboration workflow according to their expertise.

The environment we present in this paper takes up the challenge of providing a set of tools that require low effort for non-technical users but at the same time enabling easier access to advanced functionality for expert users (Siemens, 2012).
Learning Analytics, Open Learning Analytics, assessment.