Learning programming benefits from self-regulation, but novices lack support for developing these skills of cognitive control. To support their development, we designed Code Replayer, an online tool that enables novice programmers to practice programming and then replay their coding process to reflect and identify process improvements. To evaluate the impact of replaying code on self-regulation, we conducted a formative qualitative evaluation with 21 novice programmers who used Code Replayer to practice writing code. We found that after watching code replays, participants more frequently interpreted problem prompts and planned their solutions, two crucial self-regulation behaviors that novices often overlook. We interpret our results by focusing on two focal points in the design of code replays as a programming self-regulation intervention: interpreting pauses in replays and ensuring replays of struggle are more informative and less detrimental.
Assessments that can measure student understanding of concepts in a reliable and valid way are incredibly valuable in research. Unfortunately, assessments can be a source of bias, differentially impacting students along various demographic lines. Differential Item Functioning (DIF) is a method to explore assessment bias. However, DIF is primarily limited to a single binary demographic variable (e.g. white and non-white; male and female). In this paper, we describe a novel expansion of DIF methods to explore intersections of student identities. We demonstrate the use of classic DIF on a data set of 255 complete responses to a CS1 assessment using binary race and gender variables in our analyses. Then, we present the importance of intersectional DIF by running a similar analysis on intersectional data. Using these methods, we identify problematic items on the assessment that are biased against certain groups of test-takers. Our work contributes an innovative method to help interpret assessment results and inform changes to assessments.
The latest AI advancements have provided opportunities for developing automated scoring and diagnosis systems that interpret and evaluate students’ written solutions and assist teachers’ grading and evaluation, yet computer vision still represents a technical challenge in detecting and describing the numerical values and spatial locations of key elements in students’ hand-written solutions to mathematics tasks. This study reports the development and evaluation of an AI-based platform, called Visual Translator (VT), that automatically detects and describes the key visual information which is essential to the next step of auto-grading and diagnosis. The VT was trained with a private dataset of students’ handwritten solution images. Human-experts annotated the key elements in students’ solution images to build ground truth. We evaluated the VT performance by comparing the fraction value identification accuracy and location detection accuracy between VT and available LLMs against human expert annotations. Results suggested that VT surpassed GPT and Grok in fraction value identification, and also outperformed Geimini, the only LLM that supports image segmentation, in location detection. This model serves as the first step to reach the ultimate goal for classifying problem-solving strategies and error types in students’ handwritten solutions. Implications for computer vision research, auto-grading and diagnosis in K12 mathematics education are discussed.
18 September 2026 in Early Childhood Research Quarterly