Student Reasoning in Organic Chemistry
Chapter 18: Development of a Generalizable Framework for Machine Learning-based Evaluation of Written Explanations of Reaction Mechanisms from the Post-secondary Organic Chemistry Curriculum
Published:21 Dec 2022
Special Collection: 2022 ebook collection
Jeffrey R. Raker, Brandon J. Yik, Amber J. Dood, 2022. "Development of a Generalizable Framework for Machine Learning-based Evaluation of Written Explanations of Reaction Mechanisms from the Post-secondary Organic Chemistry Curriculum", Student Reasoning in Organic Chemistry, Nicole Graulich, Ginger Shultz
Download citation file:
To assess the understanding of reaction mechanisms it is necessary to ask learners what the lines, letters, arrows, and other symbols mean. Regurgitation of mechanistic representations is an insufficient measure of learning. In this chapter, we report a framework for assessing understanding through the evaluation of written explanations of what is happening and why for a broad array of reaction mechanisms taught in the postsecondary organic chemistry curriculum. We outline levels of explanation sophistication that can be used to identify opportunities for developing deeper and more meaningful understanding. This work builds on educational research on how organic chemistry students learn and develop expertise in using reaction mechanisms to predict and explain chemical transformations. Purposely considering mechanisms from a mechanistic step or mechanistic component perspective (for example, understanding of a proton transfer) has the potential to spark fresh insights for new and innovative means to facilitate learning. Our long-term goal for this work is to operationalize the framework by applying machine learning techniques to analyze written responses which will provide targeted feedback to educators and learners as they develop understanding of reaction mechanisms.