Open learning analytics (OLA) is a relatively new branch of learning analytics (LA) which emerged due to the growing demand for self-organized, networked, and lifelong learning opportunities. OLA deals with learning data collected from various learning environments and contexts, analyzed with a range of analytics methods, and for different stakeholders with diverse interests and objectives. This diversity in different dimensions of OLA is a challenge which needs to be addressed by adopting a personalized learning analytics (PLA) model. Current implementations of LA mainly rely on a predefined set of questions and indicators which is not suitable in the context of OLA where the indicators are unpredictable. In this paper we present the goal question indicator (GQI) approach for PLA and provide the conceptual, design, implementation and evaluation details of the indicator engine component of the open learning analytics platform (OpenLAP) that engages end users in the indicator generation process by supporting them in setting goals, posing questions, and self-defining
[1]
Mohamed Amine Chatti.
Personalization in technology enhanced learning: a social software perspective
,
2010
.
[2]
Ulrik Schroeder,et al.
A rule-based indicator definition tool for personalized learning analytics
,
2016,
LAK.
[3]
Ulrik Schroeder,et al.
A Modular and Extensible Framework for Open Learning Analytics
,
2018,
J. Learn. Anal..
[4]
Ulrik Schroeder,et al.
Toward an Open Learning Analytics Ecosystem
,
2017
.
[5]
Ulrik Schroeder,et al.
Data Models in Learning Analytics
,
2014,
DeLFI Workshops.