Abstract: As a field at the intersection of social and data sciences there is a strong need for quality instrumentation of teaching and learning. Yet, much of the work done in the field of Learning Analytics to date has not considered instrumentation directly, and instead has been built upon data which is the byproduct of learner activities, sometimes even pejoratively referred to as “data exhaust”. In this talk I will describe both a need for and an agenda toward exploring learning analytics instrumentation directly, where the creation, employ, and improvement of data collection instruments are of central interest. I will discuss methodological, architectural, and pragmatic considerations when it comes to the instrumentation of learning analytics systems and give specific thoughts on the need to understand and improve upon instrumentation choices when making theoretical and methodological decisions.

Bio: Christopher Brooks is an applied Computer Scientist who builds and studies the effects of educational technologies in higher education and informal learning environments. Dr. Brooks has a particular domain focus on data science education and methodological interests in predictive modeling, learning analytics, and collaborative learning. He has published widely in the areas of educational technologies and human-computer interaction and has been awarded several best papers (LAK, AIED, CHI, CSCW) with collaborators. At the University of Michigan School of Information he directs the activities of the educational technology collective (etc), a group of postdoctoral scholars, graduate students, undergraduate students, and other collaborators.