Keywords
GenAI, Programming, HAI, Think-Aloud

Technologies
ChatGPT, Python, SPSS, Verbal Protocol Analysis

This project investigates how software developers think and make decisions when using Generative AI (GenAI) tools such as ChatGPT. Using a mixed-methods design, participants complete programming tasks with or without AI assistance while verbalising their thoughts. The study examines how developers’ cognitive models of GenAI relate to trust, self-efficacy, reliance, and task satisfaction. By integrating quantitative comparisons with qualitative think-aloud data, the research aims to determine whether GenAI enhances learning and productivity or fosters overreliance, contributing to understanding human–AI interaction.

My contribution spans both qualitative and quantitative analysis. I contributed to the transcription and coding of think-aloud data using Verbal Protocol Analysis (VPA) to identify patterns in reasoning, trust, and reliance. I also helped develop post-task survey measures and analyse participants’ responses. Integrating these data supports a triangulated understanding of how cognitive models influence trust, reliance, and decision-making.