To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks
For educators and researchers studying AI-assisted learning, this work provides initial evidence that behavioral signals can indicate superficial engagement with AI code suggestions.
The paper introduces Clover, a code completion tool that logs student interactions with AI suggestions and uses attention checks to measure critical engagement. It finds that higher tab acceptance rates correlate with lower attention check performance, while longer dwell times correlate with higher performance.
AI code completion tools, such as Github Copilot, provide students with code suggestions to help them write programs. However, recent qualitative studies suggest that students fail to critically evaluate these suggestions. We present Clover, a code completion tool that logs students' interactions with code suggestions and additionally offers attention checks to probe reflective engagement during programming tasks. We also develop a taxonomy of behavioral interaction metrics for AI-assisted programming, informed by literature. We analyzed relationships between interaction patterns, engagement with attention checks, and task performance. We observed that higher rates of tab accept were associated with lower attention check performance, while increased dwell time was associated with higher attention check performance. We conclude by discussing how programming process data and attention checks might support reflective engagement in AI-assisted programming.