analiza aiqbench
This study demonstrates that AI-generated animated traces offer selective, short-term benefits for novice programmers but are heavily dependent on learner engagement profiles. The findings suggest that while these tools can enhance immediate understanding, their effectiveness is not universal and requires personalized approaches to be impactful. Consequently, the technology's utility lies in its ability to adapt to specific student contexts rather than serving as a one-size-fits-all solution for introductory CS courses.
AI-Generated Traces for Novice Programmers: Learning Effects and Learner Differences in a Multi-Institutional Study
arXiv:2606.03288v1 Announce Type: cross Abstract: Introductory programming (CS1) courses often struggle to support students' understanding of program execution. While visualizations can make execution processes explicit, their effectiveness depends on design and context, and empirical evidence for AI-generated visualizations remains limited. We propose Generated Animated Traces (GATs), AI-generated, analogy-based, narrated animations that coordinate source code, execution state, and conceptual analogies. We conduct a study at two institutions in CS1 courses (Python, N=961; Java N=151) comparing GATs to textual explanations. We measure immediate learning performance and experience, end-of-course engagement and exam performance. Results show that GATs can yield selective benefits for immediate learning, but benefits are context-dependent and short-term. We observe that GATs' influence on performance is moderated by learner engagement profiles. This finding underscores the importance of personalized approaches.
Abstract:Introductory programming (CS1) courses often struggle to support students' understanding of program execution. While visualizations can make execution processes explicit, their effectiveness depends on design and context, and empirical evidence for AI-generated visualizations remains limited. We propose Generated Animated Traces (GATs), AI-generated, analogy-based, narrated animations that coordinate source code, execution state, and conceptual analogies. We conduct a study at two institutions in CS1 courses (Python, N=961; Java N=151) comparing GATs to textual explanations. We measure immediate learning performance and experience, end-of-course engagement and exam performance. Results show that GATs can yield selective benefits for immediate learning, but benefits are context-dependent and short-term. We observe that GATs' influence on performance is moderated by learner engagement profiles. This finding underscores the importance of personalized approaches.
Computers and Society (cs.CY); Artificial Intelligence (cs.AI)
arXiv:2606.03288 [cs.CY]
(or arXiv:2606.03288v1 [cs.CY] for this version)
https://doi.org/10.48550/arXiv.2606.03288 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1145/3803400.3809346 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 231 cuvinte