How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior
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. Understanding the interplay is essential for improving developer experience and future AI assistant designs. To understand this phenomenon, we conducted a mixed-methods study with 76 developers. We first split developers into AI-assisted and non-AI groups. Each performed a programming task (either Python with API management or Java with SQL). Developers retrospectively labeled their self-reported intentions, tool-supported actions, and emotions (on a 7-point valence scale) from screen recordings, supplemented by participant surveys and interviews. Our user study resulted in a novel model, named S-IASE, with four dimensions to describe programming behavior for a given development state: intention, action, supporting tool, and emotion. Our analysis reveals several aggregated and sequential behavioral patterns. For example, for aggregated patterns, using AI assistants often led developers to focus more on actively “creating” code, evaluating, and verifying the generated results; for sequential patterns, AI-assisted participants showed emotionally stable development flows, 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 for programming. The uncovered patterns indicate that our model can provide actionable insights for improving AI assistants’ responsiveness, training developers in AI collaboration, and designing developer-centric AI studies. Our work bridges an important gap in understanding the complexities of developer-AI interaction in the programming context and sheds light on future developer-centric research directions.
Thu 9 JulDisplayed time zone: Eastern Time (US & Canada) change
10:30 - 12:30 | DevelopersJournal-First Paper / Research Papers / Ideas, Visions and Reflections / Re-routed Presentations from Past Years at MB 2.210 Chair(s): Ying Zhang | ||
10:30 20mTalk | On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors Research Papers Yuhong Liu Beihang University, YUNHE SU , Zhipeng Peng Beihang University, Zhiwen Luo Beihang University, Lin Shi Beihang University, Zhi Jin Wuhan University, Li Zhang Beihang University Pre-print | ||
10:50 10mTalk | At What Cost? Software Developers’ Well-Being in the Age of GenAI Ideas, Visions and Reflections Mariam Guizani Queen's University, Canada, Maduka Subasinghage The University of Western Australia, Sherlock A. Licorish University of Otago, Sofia Ouhbi Uppsala University Pre-print | ||
11:00 20mTalk | How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior Research Papers Yinan Wu North Carolina State University, Ze Shi (Zane) Li University of Oklahoma, Kathryn Stolee North Carolina State University, Bowen Xu North Carolina State University DOI Pre-print | ||
11:30 20mResearch paper | ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering Research Papers Md Awsaf Alam Anindya Bangladesh University of Engineering and Technology, Showvik Biswas Bangladesh University of Engineering and Technology, Anindya Iqbal Bangladesh University of Engineering and Technology Dhaka, Bangladesh, Jaydeb Sarker University of Nebraska at Omaha, Amiangshu Bosu Wayne State University Link to publication DOI Pre-print Media Attached | ||
11:50 20mTalk | Automated Extraction and Analysis of Developer's Rationale in Open Source Software Re-routed Presentations from Past Years Mouna Dhaouadi University of Montreal, Bentley Oakes Polytechnique Montréal, Michalis Famelis Université de Montréal Link to publication DOI | ||
12:10 20mTalk | Leveraging Risk Models to Improve Productivity for Effective Code Un-Freeze at Scale Journal-First Paper Audris Mockus University of Tennessee, Rui Abreu Faculty of Engineering of the University of Porto, Portugal, Peter C Rigby Meta / Concordia University, David Amsallem Meta Platforms, Inc., Parveen Bansal Meta Platforms, Inc., Kaavya Chinniah Meta Platforms, Inc., Brian Ellis Meta Platforms, Inc., Peng Fan Meta Platforms, Inc., Jun Ge Meta Platforms, Inc., Wenlei He Meta, Kelly Hirano Meta Platforms, Inc., Sahil Kumar Meta Platforms, Inc., Ajay Lingapuram Meta Platforms, Inc., W. Andrew Loe III Meta Platforms, Inc., Megh Mehta Meta Platforms, Inc., Venus Montes Meta Platforms, Inc., Maher Saba Meta Platforms, Inc., Gursharan Singh Meta Platforms, Inc., Matt Steiner Meta Platforms, Inc., Weiyan Sun Meta Platforms, Inc., Siri Uppalapati Meta Platforms, Inc., Nachiappan Nagappan Meta Platforms, Inc. | ||