Natural Language Processing-informed learning analytics for tracking and measuring aspects of argumentation
We propose to develop Natural Language Processing (NLP)-informed Learning Analytics methods to track and measure students’ argumentation in writing intensive courses and in ways that make it easy for faculty, students and scholars to use.
We identified the need to develop these learning analytics methods based on the evaluation of the pedagogical practices for teaching and assessing the abilities of students to argue and reason like a scientist in the context of Scie113 course. (see: Birol et al., 2013; Elouazizi et al. 2015).
The anticipated outcome of this project is a functional prototype tool and documented NLP methods to be used in Scie 113 and potentially in other courses at the Faculty of Science and UBC. We have the expertise to employ the well-established Natural Language Processing methods in novel ways to serve the pedagogy underlying the learning and the teaching of argumentation skills in the context of science education.
Year 1: Project Year
Year 1: Funding Year
Year 1: Project Type
Year 1: Principal Investigator
Year 1: Funded Amount
Year 1: Team Members
Gülnur Birol, Director, Science Centre for Learning and Teaching / Skylight, Faculty of Science
Gunilla Öberg, Scie 113 Director, Professor at the Institute for Resources, Environment and Sustainability, Faculty of Science