Brooks receives National Science Foundation grant to examine online learning data
Christopher Brooks, research fellow and research investigator in the School of Information, has received a $253,429 grant from the National Science Foundation for a project to examine data from online learning environments, look for ways to better predict student success and design interventions to provide support.
As high schools, community colleges and universities enroll more students in blended or online courses, the increasing amount of data coming from learning content management and massive open online course (MOOC) systems can provide insight into teaching and learning processes.
Brooks and fellow researchers Stephanie Teasley, a research professor at UMSI, and George Siemens from The University of Texas at Arlington, bring backgrounds in education, cognitive psychology, computer science and social sciences to the study and will apply a diverse set of techniques to understand how student discussions affect learning.
Current predictive modelling and learning analytics that are applied to early-warning systems for student success overwhelmingly use only coarse evaluative and demographic data, such as grades, ethnicity, gender, and student background. By employing more semantically-rich data like educational discourse, educators could better understand students’ cognitive, motivational, and emotional states, as well as their engagement with peers, instructors, and learning content.
This project, titled “Community and Capacity for Educational Discourse Research,” will conduct two scientific workshops to bring together expert educational discourse researchers to identify, elaborate upon and address the barriers that exist in the collaboration and sharing of discourse datasets.
Increasing the ability of researchers to share datasets, tools, and methodologies will broaden the applications of current techniques to new learning situations and help grow next-generation educational discourse analytics.
The study also will lead to the creation of a community of educational discourse researchers that will address ethical, technical and infrastructure issues related to sharing private identifiable data across institutions.
By building connections between learning and computational sciences, this research can support growth in the variety, quality and ability of predictive models for education and early-warning systems for student success.