Korean perspective on Learning Analytics: Development through a test bed based on Open Source


This guest blog post is the second in our new series of country reports from scholars renowned for their contribution to national and international learning analytics research. Yong-Sang Cho is leading the learning technology standards development in South Korea and is now pioneering learning analytics systems development in this country.

When I was national standards coordinator for Smart Media from 2011 to 2013, the Korean government asked me to make a framework for interoperability standards related to media technologies pertaining to education domain. To develop the standards framework my advisory committee members and I had surveyed and evaluated each item captured from standardization organizations and research institutions. During this survey period, in 2012, I found a very interesting potential standardization item, titled data analytics for learning service. Around 2012, one of the hottest emerging technologies around the world was Big Data and data analytics; and global research institutions competed in making reports about what is the concept of Big Data and how data analytics can change society.

According to this trend I got interest to adopt data analytics for improving education service in terms of personalized learning. At that time, however, we just found simple cases, which were to use learning activity data as well as log files to present on the dashboard of the learning platform. I thought data analytics, namely learning analytics, could be understood as a big picture beyond log type data analysis. Probably when people see the results from their activity analysis such as learning or job training, they have curiosity for what is my current status on required competency level and weaknesses compared with my similar group. This simple expectation imply that learning analytics should deliver insight through multi-dimensional analysis and therefore needs to be combined with competency map pertaining to curriculum standards. This prospect and assumption was a starting point to my three-years research project funded by Korean government from 2014 to 2017. This standardization R&D project is composed of three parts:

  • First task is to design workflow and to setup the test bed for reference model of learning analytics using open source software. The test bed was separated in two parts; first part is a data generation area such as LMS/VLE and application for digital textbook, and the other is data storing and analyzing area similar with Big Data analytics platform.
  • Second task is to develop standards for metric profile and data collecting API. This task is tightly combined with IMS Caliper project of IMS Global Learning Consortium. To improve accuracy for analytics my team believes that standardized data metrics is a mandatorily requirement rather than individual log data format.
  • The last task is to design a linked data framework for curriculum standards to connect with digital resources. This linked data profile is very useful when an analytics platform find weaknesses on the competency map for learners. It means that the analytics platform shows recommended personalized learning path with learning material derived from linked data search engine.

Furthermore, I’ve been expecting that learning analytics has the capability to extend to learning portfolio services because learners can get self-reflection through analytics services as describe above. The learning portfolio system may be reformed from current manual operation environments to a data driven workflow as described in the figure below.


Finally, I would like to emphasize a balanced view of emerging technology development, in particular, such as learning analytics. Even though technology and service providers have made more positive images for learning analytics with top priority, someone should prepare and argue the other side, namely defensive features, such as privacy protection and accessibility. For this purpose, my team is investigating to identify mechanisms with a secured way between learning data provider and consumer, and to define an accessibility metadata matching mechanism pertaining mobile environments. Hopefully, the whole efforts of this Korean research projects can be more widely accepted and shared with global communities like the one supported by the LACE project.

View Twitter conversations and metrics using [Topsy]

Yong-Sang Cho is a principal researcher in Korea Education & Research Information Service (KERIS) and convenor of ISO/IEC JTC1 SC34 and SC36. His twitter id is @zzosang

About Author

Leave A Reply