Replication Package for the Paper: "A Machine Learning Based Ensemble Method for Automatic Multiclass Classification of Decisions: A Study of the Hibernate Developer Mailing List"

This is the replication package for the paper: "A Machine Learning Based Ensemble Method for Automatic Classification of Decisions: A Study of the Hibernate Developer Mailing List". It contains the source code and dataset of our experiment for the replication by other researchers. In the meanwhile, we provide brief description of the files in the replication package below. <strong>1. code folder</strong> <em>experiment.py </em>contains the source code for our experiment, which is conducted on Windows 10 and Python 3.7.0. <strong>Note that you may get slightly</strong> <strong>different experiment results when conducting the experiments on different environment configurations.</strong> <em>requirement.txt</em> records all the installation packages and their version numbers needed for the current program to run. You can use "<em>pip install -r requirement.txt</em>" to rebuild the project and install all dependencies. <strong>Note that you may get slightly different experiment results when using different packages or versions. </strong> <strong>2. dataset folder</strong> <em>decisions.xlsx </em>contains 844 labelled sentence-level decisions from the Hibernate developer mailing list.

本数据集为论文《基于机器学习的决策自动分类集成方法：Hibernate开发者邮件列表研究》的复现包，包含供其他研究者复现实验所需的源代码与实验数据集。下文将对复现包内的文件进行简要说明。
1. **代码文件夹（code folder）**
* *experiment.py*：本实验的源代码文件，基于Windows 10与Python 3.7.0环境开发。**请注意：在不同环境配置下执行实验，可能会得到略有差异的实验结果。**
* *requirement.txt*：记录了当前程序运行所需的全部安装包及其版本号，可通过命令"pip install -r requirement.txt"完成项目重构与所有依赖项的安装。**请注意：使用不同版本的依赖包，可能会导致实验结果存在细微差异。**
2. **数据集文件夹（dataset folder）**
* *decisions.xlsx*：包含来自Hibernate开发者邮件列表的844条标注语句级决策样本。