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

TL;DR

This work tackles improving understanding in Parsons-problem scaffolding for novice programmers by integrating multi-level textual explanations into an LLM-driven system, CodeTailor. It describes real-time, personalized problem generation, dynamic difficulty, and diverse explanations—subgoal guidance, block- and atom-level clarifications, and post-solution self-explanations—to promote active problem-solving and deeper comprehension. The approach aims to enhance instructional benefits, with planned classroom evaluations to quantify learning gains and engagement. The design builds on prior evidence that Parsons problems boost engagement but may fall short on conceptual understanding, offering a practical path toward richer, explainable programming scaffolds.

Abstract

Novice programmers need to write basic code as part of the learning process, but they often face difficulties. To assist struggling students, we recently implemented personalized Parsons problems, which are code puzzles where students arrange blocks of code to solve them, as pop-up scaffolding. Students found them to be more engaging and preferred them for learning, instead of simply receiving the correct answer, such as the response they might get from generative AI tools like ChatGPT. However, a drawback of using Parsons problems as scaffolding is that students may be able to put the code blocks in the correct order without fully understanding the rationale of the correct solution. As a result, the learning benefits of scaffolding are compromised. Can we improve the understanding of personalized Parsons scaffolding by providing textual code explanations? In this poster, we propose a design that incorporates multiple levels of textual explanations for the Parsons problems. This design will be used for future technical evaluations and classroom experiments. These experiments will explore the effectiveness of adding textual explanations to Parsons problems to improve instructional benefits.

Figures (4)

• Figure 1: A write-code box (left) with a pop-up personalized Parsons problem as scaffolding (right).
• Figure 2: A subgoal list about the Parsons problem solution.
• Figure 3: Block-level and atom-level explanations for the finished Parsons blocks.
• Figure 4: Students will receive a menu-based self-explanation question after solving the Parsons problem.