|
|
Paper: |
Using Machine Learning to Improve Student Writing About Science |
Volume: |
537, ASP 2022: A Virtual Conference |
Page: |
6 |
Authors: |
Wenger, M.; Impey, C.; Danehy, A.; Buxner, S. |
Abstract: |
We are using a machine learning approach to help college students distinguish legitimate science from misinformation and to help non-science majors write effectively about science topics. We are using a neural network trained to identify science misinformation and applying it to undergraduate science writing. The neural network will search student writing assignments for legitimate science explanations and scientific arguments in the same way it examines online articles to identify misinformation. This tool can be used in classes of all sizes but will be particularly useful in large introductory science classes for non-science majors, with the goal of teaching students 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. |
|
|
|
|