Automated scoring of free drawings or images as responses has yet to be used in large-scale assessments of student achievement. In this study, we propose artificial neural networks to classify these types of graphical responses from a TIMSS 2019 item. We are comparing classification accuracy of convolutional and feed-forward approaches. Our…

Effort to determine teachers' effects on students has been continuously made with national data. However, paucity of research has been conducted on how teachers' instructional strategies impact on student learning with national data, although instructional theories suggest a direct relationship between instructional strategies and learning…