Your browser (Internet Explorer 7 or lower) is out of date. It has known security flaws and may not display all features of this and other websites. Learn how to update your browser.


Learning Analytics at “Small” Scale: Exploring A Complexity-Grounded Model for Assessment Automation

Publication Type:

Journal Article


Journal of Universal Computer Science, Issue Accepted (2014)


learning analytics


This study proposes a process-oriented, automatic, formative assessment model for small group learning through the lens of complex systems theory using a small dataset from a technology-mediated environment. We first conceptualize small
group learning as a complex system and explain how group dynamics and interaction can be modeled via theoretically-sound, yet simple rules. These rules are then operationalized to build temporally-embodied measures, where varying weights are
assigned to the same measures according to their significance during different time stages based on the golden ratio concept. This theory-based measure construction method in combination with a correlation-based feature subset selection algorithm
accomplishes the goal of data dimensionality reduction, contextualizing these measures within a semantic background and in turn becomes easier for teachers to understand. Further, due to the fact that sometimes small data sets are generated from
education discipline, a Tree-Augmented Naïve Bayes classifier was coded to develop the assessment model which achieves the best accuracy (95.8%) as compared to baseline models. Finally, we describe a web-based tool that visualizes time-series
activities, assesses small group learning automatically, and also offers actionable intelligence for teachers to provide real-time support and intervention to students. Theoretical and methodological implications for small group learning and learning
analytics as a whole are then discussed.