Taiwanese perspective on Learning Analytics: Identifying who will succeed

0

This guest blog post is the third in our new series of country reports from scholars renowned for their contribution to national and international learning analytics research. Shu-Fen Tseng of the Big Data and Digital Convergence Center at Yuan Ze University reports from Taiwan.

Visualization, dropout diagnosis and prediction, and MOOCs are the three focus areas of Taiwanese research and implementation activities within learning analytics.

The Big Data and Digital Convergence Center at Yuan Ze University is the first academic institution in Taiwan that has a specific focus on Learning Analytics research. Yuan Ze University is one of the top 17 universities and research centers that is selected by the Ministry of Education to participate the “Aim for the Top University Plan” project. With the goal of becoming a world-class research center in Asia and around the world, the Big Data and Digital Convergence Center is expected to play the leading role in digital convergence and big data-related research.

The learning analytic team in the Big Data and Digital Convergence Center focuses on three research topics:

(1) Learning analytics and visualization: Applying open student modeling techniques, this team has built a visualized analytic system, named the CVA-YZU (Core competency Visualized Analytics of Yuan Ze University), for assisting students to understand their status in relation to core competencies. Three features are developed in the CVA-YZU system: An Inspection Tool for matching courses and core competency relationship, Nine Radar Charts for students’ evaluation of core competencies, and a Ranking Table for students’ core competencies visualized by different colors. The CVA-YZU offers a unique tool for students to evaluate their core competencies in comparison with their current colleagues and with those who graduated.

(2) Dropout diagnosis and prediction: Dropout diagnosis and prediction research aims to monitor and predict student’s learning performance and identifying potential risk of dropout students. Data collection and analytic techniques are employed in both the secondary and tertiary educational institutes to provide timely monitoring and to alert teachers to at-risk students before they drop out. Research interests in this aspect include: risk analysis and prediction modelling of dropping out and lacking behind in learning, grouping the high-risk students and create a priority list, collaborating with selected schools to build the early warning system, and evaluating the effectiveness of early warning system intervention.

(3) Evaluation of Massive Open Online Courses (MOOCs): Yuan Ze University is one of few selected universities that have received a grant from Ministry of Education to provide MOOCs. By focusing on user- and data-driven research, this project collects learning analytic data from MOOCs. One of the main objectives is to understand how students learn and offer insight to what engages or disengages them in the MOOC learning environments. The effectiveness of online learning environments and features are examined to expand our knowledge about how students respond to these learning tools. More specific, this project aims at profiling who will succeed or drop out in MOOCs, investigating learning footprints and behavior patterns, distinguishing the passing and failing patterns, and discovering how learning environments and online features will facilitate students’ performance.


View Twitter conversations and metrics using [Topsy]

Shu-Fen Tsen is an associate professor of Information Management Department at Yuan Ze University  in Taiwan. In addition, she is a Research Fellow in the Big Data and Digital Convergence Center at Yuan Ze University.
Share.

About Author

Leave A Reply