Home > Research > Publications & Outputs > Exploring the Problems, their Causes and Soluti...

Electronic data

  • JSS_accepted

    Accepted author manuscript, 1.32 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow. / Zhou, Xiyu; Liang, Peng; Zhang, Beiqi et al.
In: Journal of Systems and Software, Vol. 219, 112204, 31.01.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Zhou, X, Liang, P, Zhang, B, Li, Z, Ahmad, A, Shahin, M & Waseem, M 2025, 'Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow', Journal of Systems and Software, vol. 219, 112204. https://doi.org/10.1016/j.jss.2024.112204

APA

Zhou, X., Liang, P., Zhang, B., Li, Z., Ahmad, A., Shahin, M., & Waseem, M. (2025). Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow. Journal of Systems and Software, 219, Article 112204. https://doi.org/10.1016/j.jss.2024.112204

Vancouver

Zhou X, Liang P, Zhang B, Li Z, Ahmad A, Shahin M et al. Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow. Journal of Systems and Software. 2025 Jan 31;219:112204. Epub 2024 Sept 7. doi: 10.1016/j.jss.2024.112204

Author

Zhou, Xiyu ; Liang, Peng ; Zhang, Beiqi et al. / Exploring the Problems, their Causes and Solutions of AI Pair Programming : A Study on Git Huband Stack Overflow. In: Journal of Systems and Software. 2025 ; Vol. 219.

Bibtex

@article{11343485c70843e69cc0401f5374965e,
title = "Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on Git Huband Stack Overflow",
abstract = "With the recent advancement of Artificial Intelligence (AI) and Large Language Models (LLMs), AI-based code generation tools become a practical solution for software development. GitHub Copilot, the AI pair programmer, utilizes machine learning models trained on a large corpus of code snippets to generate code suggestions using natural language processing. Despite its popularity in software development, there is limited empirical evidence on the actual experiences of practitioners who work with Copilot. To this end, we conducted an empirical study to understand the problems that practitioners face when using Copilot, as well as their underlying causes and potential solutions. We collected data from 473 GitHub issues, 706 GitHub discussions, and 142 Stack Overflow posts. Our results reveal that (1) Operation Issue and Compatibility Issue are the most common problems faced by Copilot users, (2) Copilot Internal Error, Network Connection Error, and Editor/IDE Compatibility Issue are identified as the most frequent causes, and (3) Bug Fixed by Copilot, Modify Configuration/Setting, and Use Suitable Version are the predominant solutions. Based on the results, we discuss the potential areas of Copilot for enhancement, and provide the implications for the Copilot users, the Copilot team, and researchers.",
author = "Xiyu Zhou and Peng Liang and Beiqi Zhang and Zengyang Li and Aakash Ahmad and Mojtaba Shahin and Muhammad Waseem",
year = "2025",
month = jan,
day = "31",
doi = "10.1016/j.jss.2024.112204",
language = "English",
volume = "219",
journal = "Journal of Systems and Software",
issn = "0164-1212",
publisher = "Elsevier Inc.",

}

RIS

TY - JOUR

T1 - Exploring the Problems, their Causes and Solutions of AI Pair Programming

T2 - A Study on Git Huband Stack Overflow

AU - Zhou, Xiyu

AU - Liang, Peng

AU - Zhang, Beiqi

AU - Li, Zengyang

AU - Ahmad, Aakash

AU - Shahin, Mojtaba

AU - Waseem, Muhammad

PY - 2025/1/31

Y1 - 2025/1/31

N2 - With the recent advancement of Artificial Intelligence (AI) and Large Language Models (LLMs), AI-based code generation tools become a practical solution for software development. GitHub Copilot, the AI pair programmer, utilizes machine learning models trained on a large corpus of code snippets to generate code suggestions using natural language processing. Despite its popularity in software development, there is limited empirical evidence on the actual experiences of practitioners who work with Copilot. To this end, we conducted an empirical study to understand the problems that practitioners face when using Copilot, as well as their underlying causes and potential solutions. We collected data from 473 GitHub issues, 706 GitHub discussions, and 142 Stack Overflow posts. Our results reveal that (1) Operation Issue and Compatibility Issue are the most common problems faced by Copilot users, (2) Copilot Internal Error, Network Connection Error, and Editor/IDE Compatibility Issue are identified as the most frequent causes, and (3) Bug Fixed by Copilot, Modify Configuration/Setting, and Use Suitable Version are the predominant solutions. Based on the results, we discuss the potential areas of Copilot for enhancement, and provide the implications for the Copilot users, the Copilot team, and researchers.

AB - With the recent advancement of Artificial Intelligence (AI) and Large Language Models (LLMs), AI-based code generation tools become a practical solution for software development. GitHub Copilot, the AI pair programmer, utilizes machine learning models trained on a large corpus of code snippets to generate code suggestions using natural language processing. Despite its popularity in software development, there is limited empirical evidence on the actual experiences of practitioners who work with Copilot. To this end, we conducted an empirical study to understand the problems that practitioners face when using Copilot, as well as their underlying causes and potential solutions. We collected data from 473 GitHub issues, 706 GitHub discussions, and 142 Stack Overflow posts. Our results reveal that (1) Operation Issue and Compatibility Issue are the most common problems faced by Copilot users, (2) Copilot Internal Error, Network Connection Error, and Editor/IDE Compatibility Issue are identified as the most frequent causes, and (3) Bug Fixed by Copilot, Modify Configuration/Setting, and Use Suitable Version are the predominant solutions. Based on the results, we discuss the potential areas of Copilot for enhancement, and provide the implications for the Copilot users, the Copilot team, and researchers.

U2 - 10.1016/j.jss.2024.112204

DO - 10.1016/j.jss.2024.112204

M3 - Journal article

VL - 219

JO - Journal of Systems and Software

JF - Journal of Systems and Software

SN - 0164-1212

M1 - 112204

ER -