This repository contains the survey and associated materials used in the paper GitHub Copilot: A Systematic Study, presented at the Ital-IA 2024 conference.
This study explores the applications, strengths, and limitations of GitHub Copilot as an AI-powered code generation tool. By analyzing user feedback, we aim to provide insights into the usability, reliability, and impact of Copilot on software development workflows.
To reference this study, please use the following citation:
@inproceedings{DBLP:conf/ital-ia/BenettiF24,
author = {Alessandro Benetti and
Michele Filannino},
editor = {Sergio Di Martino and
Carlo Sansone and
Elio Masciari and
Silvia Rossi and
Michela Gravina},
title = {GitHub Copilot: A Systematic Study},
booktitle = {Proceedings of the Ital-IA Intelligenza Artificiale - Thematic Workshops
co-located with the 4th {CINI} National Lab {AIIS} Conference on Artificial
Intelligence (Ital-IA 2024), Naples, Italy, May 29-30, 2024},
series = {{CEUR} Workshop Proceedings},
volume = {3762},
pages = {6--11},
publisher = {CEUR-WS.org},
year = {2024},
url = {https://ceur-ws.org/Vol-3762/489.pdf},
timestamp = {Fri, 11 Oct 2024 07:47:20 +0200},
biburl = {https://dblp.org/rec/conf/ital-ia/BenettiF24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}