/analyzing-shared-conversation

This repository contains the dataset, codes and other files related to our paper "An Empirical Study on Developers' Shared Conversations with ChatGPT in GitHub Pull Requests and Issues"

Primary LanguageJupyter Notebook

Welcome to the official repository of: An Empirical Study on Developers' Shared Conversations with ChatGPT in GitHub Pull Requests and Issues.

This is the replication package of our paper An Empirical Study on Developers' Shared Conversations with ChatGPT in GitHub Pull Requests and Issues which has been published in Empirical Software Engineering (EMSE).

Authors: Huizi Hao, Kazi Amit Hasan, Hong Qin, Marcos Macedo, Yuan Tian, Steven H. H. Ding , Ahmed E. Hassan

Folder structure

├── data_preprocessing
├── RQ1
│ |── rq1 data 
├── RQ2
│ ├── rq2 data
│ |── code of markov transition graph
├── RQ3
│ ├── rq3 data
│ |── code of sankey graphs

How to run

Ensure you have Python 3.8 or higher installed. In your terminal, in the same folder as this README file, execute the following commands:

  1. Clone the repository by running
  2. Run pip install -r requirements.txt
  3. To run the notebooks of RQ2 and RQ3, make sure you have jupyter/jupyterlab installed in your machine.

Citation

If you find this research useful, please consider citing our paper as follows:

@article{hao2024empirical,
  title={An Empirical Study on Developers Shared Conversations with ChatGPT in GitHub Pull Requests and Issues},
  author={Hao, Huizi and Hasan, Kazi Amit and Qin, Hong and Macedo, Marcos and Tian, Yuan and Ding, Steven HH and Hassan, Ahmed E},
  journal={arXiv preprint arXiv:2403.10468},
  year={2024}
}