1B-2 oral - Using Machine Learning to Improve Student Writing About Science
Thursday, December 8, 2022
10:00 AM – 10:50 AM PT
Chris Impey, PhD – Distinguished Professor of Astronomy & Astronomer, Astronomy, The University of Arizona; Alexander Danehy – Software Engineer, Astronomy, The University of Arizona; Sanlyn Buxner, PhD – Associate Research Professor, Teaching/Learning and Sociocultural Studies, The University of Arizona
Education Program Manager The University of Arizona, Arizona, United States
We are using a machine learning approach help college students identify legitimate science from misinformation and to help non-science majors write effectively about science topics. Neural networks have been trained to identify claims and evidence in articles online. We are using this same approach for undergraduate science writing. The trained neural network is applied to writing assignments in large introductory science classes for non-science majors, with the goal of teaching students in how to recognize and ultimately construct legitimate scientific arguments. The tool will also be used by instructors for formative assessment and to give students constructive feedback on their writing assignments.