Prior work has shown a lack of quality professional development (PD) programs specifically targeted for early elementary teachers to improve their knowledge and self-efficacy around teaching coding in their classrooms. Whereas traditional PD programs in this area have relied upon in-person workshops, the COVID-19 pandemic necessitated the need to…

As students learn how to program, both their programming code and their understanding of it evolves over time. In this work, we present a general data-driven approach, named "Temporal-ASTNN" for modeling student learning progression in open-ended programming domains. Temporal-ASTNN combines a novel neural network model based on abstract…