How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior

2026-03-28

AI Summary

This study addresses the insufficient modeling of the complex interplay between implicit psychological dimensions—such as intent and emotion—and observable behaviors among developers in AI-assisted programming. To bridge this gap, the authors propose the S-IASE framework, a four-dimensional model encompassing Intent, Action, Supporting tools, and Emotion. Employing a mixed-methods approach—including screen-recording retrospective annotation, semi-structured interviews, surveys, and behavioral sequence analysis—the research systematically characterizes programming behavior patterns under AI assistance. Findings reveal that AI-assisted developers exhibit greater focus on code generation and validation and demonstrate more stable emotional states compared to non-AI users, who experience significantly higher emotional volatility. The study not only uncovers novel relationships between emotional stability and behavioral focus but also identifies deeper psychological phenomena such as imposter syndrome, thereby validating the explanatory power and efficacy of the S-IASE model.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Embodied AI

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Artificial Intelligence (AI) is reshaping how developers adopt software engineering practices, yet the multi-dimensional nature of developer-AI interaction remains under-explored. Prior studies have primarily examined dimensions observable from developer activities such as"Prompt crafting"and"Code Editing", overlooking how hidden intentions and emotional dimensions intertwine with concrete actions during AI-assisted programming. To understand this phenomenon, we conducted a mixed-methods study with 76 developers split into AI-assisted and non-AI groups. Each performed programming tasks (Python with API management or Java with SQL). Developers retrospectively labeled their self-reported intentions, tool-supported actions, and emotions from screen recordings, supplemented by surveys and interviews. Our user study resulted in a novel model named S-IASE with four dimensions to describe programming behavior: intention, action, supporting tool, and emotion for a given development state. Our analysis reveals aggregated and sequential behavioral patterns. For example, using AI assistants often makes developers more focused on actively creating code, evaluating, and verifying generated results. AI-assisted participants showed emotionally stable development flow, as opposed to non-AI-assisted participants who experienced more fluctuating emotions. Interviews revealed further nuance: some developers reported impostor-like feelings, expressing guilt or self-doubt about relying on AI. Our work bridges an important gap in understanding the complexities of developer-AI interaction in programming context.

Problem

• developer-AI interaction
• programming behavior
• intentions
• emotions
• AI-assisted programming

Innovation

• developer-AI interaction
• programming behavior modeling
• S-IASE model
• emotional dynamics
• mixed-methods study