A5005794732- Online Learning and Analytics
- Online and Blended Learning
- Innovative Teaching and Learning Methods
- Explainable Artificial Intelligence (XAI)
- Advanced Graph Neural Networks
- Machine Learning and Data Classification
- Social Capital and Networks
Monash University
2023
University of Edinburgh
2018-2021
Research into self-regulated learning has traditionally relied upon self-reported data. While there is a rich body of literature that extracted invaluable information from such sources, it suffers number shortcomings. For instance, been shown surveys often provide insight students' perceptions about rather than how students actually employ study tactics and strategies. Accordingly, recent research sought to assess strategies and, by extension, their via trace data collected digital...
Student engagement is often considered an overarching construct in educational research and practice. Though frequently employed the learning analytics literature, has been subjected to a variety of interpretations there little consensus regarding very definition construct. This raises grave concerns with regards validity: namely, do these varied metrics measure same thing? To address such concerns, this paper proposes, quantifies, validates model which both grounded theoretical literature...
The widespread adoption of digital e-learning environments and other learning technology has provided researchers with ready access to large quantities data. Much this data comes from discussion forums been studied analytical methods drawn social network analysis. However, within body research there exists considerable variation in the definition what constitutes a tie, consequences choice are rarely described or examined. This paper presents findings two distinct regarding different tie...
In this article, we empirically validate Tinto's Student Integration model, in particular, the predictions model makes regarding both students' academic outcomes and their dropout decisions. doing so, analyze three decades' worth of student enrollments at an Australian university present a novel methodological approach using graph embedding techniques to capture structural neighborhood-based features co-enrollment network. keeping with find that not only do these embedded representations...