Analysis of Student Behaviour in Habitable Worlds Using Continuous Representation Visualization

Main Article Content

Zachary A Pardos
Lev Horodyskyj

Abstract

We introduce a novel approach to visualizing temporal clickstream behaviour in the context of a degree-satisfying online course, Habitable Worlds, offered through Arizona State University. The current practice for visualizing behaviour within a digital learning environment is to generate plots based on hand-engineered or coded features using domain knowledge. While this approach has been effective in relating behaviour to known phenomena, features crafted from domain knowledge are not likely well suited to making unfamiliar phenomena salient and thus can preclude discovery. We introduce a methodology for organically surfacing behavioural regularities from clickstream data, conducting an expert in-the-loop hyperparameter search, and identifying anticipated as well as newly discovered patterns of behaviour. While these visualization techniques have been used before in the broader machine-learning community to better understand neural networks and relationships between word vectors, we apply them to online behavioural learner data and go a step further, exploring the impact of the parameters of the model on producing tangible, non-trivial observations of behaviour that suggest pedagogical improvement to the course designers and instructors. The methodology introduced in this paper led to an improved understanding of passing and non-passing student behaviour in the course and is applicable to other datasets of clickstream activity where investigators and stakeholders wish to organically surface principal patterns of behaviour.

Article Details

How to Cite
Pardos, Z. A., & Horodyskyj, L. (2019). Analysis of Student Behaviour in Habitable Worlds Using Continuous Representation Visualization. Journal of Learning Analytics, 6(1), 1–15. https://doi.org/10.18608/jla.2019.61.1
Section
Research Papers
Author Biographies

Zachary A Pardos, University of California, Berkeley, USA

Dr. Pardos is an Assistant Professor at UC Berkeley in a joint position between the Information School and the School of Education. His focal areas of study are knowledge representation and personalized supports leveraging big data in education. He earned his PhD in Computer Science at WPI and comes to UC Berkeley after a post-doc at MIT CSAIL studying Massive Open Online Courses. At UC Berkeley he directs the Computational Approaches to Human Learning (CAHL) research lab and teaches courses on Data Mining and Analytics, Digital Learning Environments, and Machine Learning in Education.

Lev Horodyskyj, Arizona State University

Course Coordinator (ASU Online/School of Earth and Space Exploration, ASU)