Integrating Personalized Parsons Problems with Multi-Level Textual Explanations to Scaffold Code Writing

Novice programmers need to learn how to write basic code but often face difficulties when coding independently. To assist struggling students, we have recently implemented personalized Parsons problems as a pop-up scaffolding. Students found them to be more engaging and helpful for learning compared to simply receiving the correct answer, such as the response they might get from Large Language Model (LLM) tools like ChatGPT. However, a drawback of using Parsons problems as scaffolding is that students may be able to put the code blocks back in place without fully understanding the rationale of the correct solution. As a result, the learning benefits of such scaffolding are compromised. Our goal is to enhance the advantages of using personalized Parsons problems as scaffolding by improving their comprehension through code explanations. In this poster, we propose designs that incorporate multiple levels of textual explanations in the Parsons problems. This design will be used for future technical evaluation and classroom experiments. These experiments will explore the effectiveness of adding textual explanations to Parsons problems to improve instructional benefits.