Principal Investigator (PI): A/P Andy Khong
, School of Electrical & Electronic Engineering
Co-PI: Huaqing Hong
, Research Scientist, Centre for Research and Development in Learning
Collaborator: Paul Gagnon
, Director, e-Learning and IT Services, Lee Kong Chian School of Medicine
Funding Agency: CRADLE@NTU start-up grant
Nanyang Technological University (NTU) positioned itself as one of Singapore’s ringleaders in the exploitation of education technologies. The University-wide launch of the $Sg 70 million Technology-Enabled Learning
in 2014 aimed to migrate at least half of the course modules online with interactive features throughout a five-year timeline. The move has since become a game-changer in transmitting online multimedia course information and promoting students’ initiative and resourcefulness to take ownership of their own knowledge gains through team-based learning
(TBL) and self-directed learning
Consequentially, the students’ real-time access and use of education technologies leave behind tractable online trails that can characterise their learning behaviours and outcomes. The Centre for Research and Development in Learning (CRADLE@NTU), together with the School of Electrical and Electronic Engineering
and the Lee Kong Chian School of Medicine
’s (LKCSOM) e-Learning and IT Services, banks on these user-generated data in e-Learning ecosystems to analyse the varying levels of students’ online engagement.
The research project is designed to develop a computational modelling framework of student engagement in NTU's SDL and TBL environment, taking LKCSOM’s TBL ecosystem as the starting point. The ecosystem, designed to seamlessly integrate with and support the delivery of a mobile, self-directed and paperless curriculum experience, builds on an e-Learning framework known as TERASA (Technology Enabled Resources, Activities, Support and Assessment), which was recently adapted to an Integrated Learning Analytics Visualization System (iLAVS) used to monitor and track in real-time student access and use of the various e- Learning resources.
The computational modelling framework is expected to dynamically report empirical data related to emerging student online engagement behaviours and patterns, identify the salient variables related to the effectiveness of the learning ecosystem, and eventually assist in predicting students’ learning outcomes and behaviours.
Focusing on students’ online engagement, three aspects of interest are: i) total time on task, ii) continuity, or sustained time on a single task, and iii) emerging correlations between time on task and student performance on formative assessments, over the course of each teaching block within and across the academic years.
Results of data analysis may impact the level of students’ engagement in SDL and TBL, and inform the design of e-Learning ecosystems for universal use.