Incorporating non-verbal data streams is essential to understanding the dynamics of interaction within collaborative learning environments in which a variety of verbal and non-verbal modes of communication intersect. However, the complexity of non-verbal data -- especially gathered in the wild from collaborative learning contexts -- demands…

Classroom sensing systems can capture data on teacher-student behaviours and interactions at a scale far greater than human observers can. These data, translated to multi-modal analytics, can provide meaningful insights to educational stakeholders. However, complex data can be difficult to make sense of. In addition, analyses done on these data…

Model evaluation -- the process of making inferences about the performance of predictive models -- is a critical component of predictive modelling research in learning analytics. We survey the state of the practice with respect to model evaluation in learning analytics, which overwhelmingly uses only naïve methods for model evaluation or…

Recordings of human interaction data can be organized into temporal representations with different affordances. We use audio data of a learning-related discussion analyzed for its low-level emotional indicators and divided into four phases, each characterized by an overarching emotion. After arguing for the relevance of emotion to learning, we…

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…

Designing, validating, and deploying learning analytics tools for instructors or students is a challenge that requires techniques and methods from different disciplines, such as software engineering, human-computer interaction, computer graphics, educational design, and psychology. Whilst each has established its own design methodologies, we now…

Dealing with the vast quantities of text that students generate in Massive Open Online Courses (MOOCs) and other large-scale online learning environments is a daunting challenge. Computational tools are needed to help instructional teams uncover themes and patterns as students write in forums, assignments, and surveys. This paper introduces to the…

Educational data science (EDS) is an emerging, interdisciplinary research domain that seeks to improve educational assessment, teaching, and student learning through data analytics. Teachers have been portrayed in the EDS literature as users of pre-constructed data dashboards in educational technologies, with little consideration given to them as…

There is an urgent need for our educational system to shift assessment regimes from a narrow, high-stakes focus on grades, to more holistic definitions that value the qualities that lifelong learners will need. The challenge for learning analytics in this context is to deliver actionable assessments of these hard-to-quantify qualities, valued by…

As a further step towards maturity, the field of learning analytics (LA) is working on the definition of frameworks that structure the legal and ethical issues that scholars and practitioners must take into account when planning and applying LA solutions to their learning contexts. However, current efforts in this direction tend to be focused on…

Prototype work can support the creation of data visualizations throughout the research and development process through paper prototypes with sketching, designed prototypes with graphic design tools, and functional prototypes to explore how the implementation will work. One challenging aspect of data visualization work is coordinating the expertise…

Central to the mission of most educational institutions is the task of preparing the next generation of citizens to contribute to society. Schools, colleges, and universities value a range of outcomes--e.g., problem solving, creativity, collaboration, citizenship, service to community--as well as academic outcomes in traditional subjects. Often…

Accurate and early predictions of student performance could significantly affect interventions during teaching and assessment, which gradually could lead to improved learning outcomes. In our research, we seek to identify and formalize temporal parameters as predictors of performance ("temporal learning analytics" or TLA) and examine…

A core goal for most learning analytic projects is to move from small-scale research towards broader institutional implementation, but this introduces a new set of challenges because institutions are stable systems, resistant to change. To avoid failure and maximize success, implementation of learning analytics at scale requires explicit and…

Promoting blog content is a social activity--a means of communicating one student's appreciation of another student's work. This article explores the feasibility of using student promotions of content, in a blogosphere, to identify quality content, and implications for students and instructors. We show that students actively and voluntarily…