Journal of Science Education and Technology 2021

3 papers
The 2021 edition of the Journal of Science Education and Technology emphasized the integration of machine learning into science assessment frameworks. Research focused on the development and implementation of automated scoring systems for multi-dimensional assessments in subjects like chemistry and physics. These studies explored how computational tools can assist in innovative assessment practices while addressing the theoretical foundations required for such technologies in educational contexts. Key contributions from authors such as Joseph Krajcik, Barbara Schneider, and James W. Pellegrino examined the validity of machine learning-based assessments. This work included the development of validity inferential networks to ensure that automated systems accurately reflect student performance according to modern science standards. Collectively, the research from this year highlights a trend toward using advanced data science techniques to evaluate complex learning outcomes in science education.

Papers

Title
On the Validity of Machine Learning-based Next Generation Science Assessments: A Validity Inferential Network
Practices and Theories: How Can Machine Learning Assist in Innovative Assessment Practices in Science Education
Using Machine Learning to Score Multi-Dimensional Assessments of Chemistry and Physics