Feed

Artificial intelligence (AI) incorporates the applications of machine-learning systems dominantly within the automated assessment and intelligent tutoring systems. These AI applications have promising potential to increase capacity within science, technology, engineering, and mathematics (STEM) education by supporting the social and cognitive development and learning experiences of students.

Artificial Intelligence (AI) technologies, including machine learning and data mining, have been extensively adopted to automate scoring of student responses to performance-based assessment tasks in classrooms, subsequently generating informative assessment reports. Although the innovative potential of these technologies is widely acknowledged, teachers often find it challenging to utilize these assessment data for instructional decisions.

Investigating AI's role in educational assessments, this study compares AI- provided and teacher scores of hand-drawn scientific models by Multilingual Language Learners (MLLs) in elementary classrooms. Using Convolutional Neural Networks (CNN) for scoring, we aligned AI assessments with those of experienced teachers. The results show moderate agreement (Kappa = 0.326), with AI favoring mid-range scores, while teachers provided a broader score spectrum. This suggests AI's consistency may miss the interpretive nuances teachers offer.

Haudek, K. C., & Zhai, X. (2024). Examining the effect of assessment construct characteristics on machine learning scoring of scientific argumentation. International Journal of Artificial Intelligence in Education. 34(4) https://doi.org/10.1007/s40593-023-00385-8