一句话：提出 ChatBR，利用 ChatGPT 自动评估并补全缺陷报告中缺失的关键信息，以提升报告质量。
缺陷报告通常包含观察行为、期望行为和复现步骤等关键信息，能帮助开发者高效定位与修复缺陷。然而，缺陷日益复杂且报告者经验有限，大量报告缺失这些关键信息。现有基于机器学习或信息检索的方法虽可检测并补充缺失信息，但其性能高度依赖缺陷报告数据集规模与质量。本文提出 ChatBR，利用 ChatGPT 对缺陷报告质量进行自动评估与改进。摘要未报告具体实验设置与量化结果，因此其实际效果与评估方式需参见全文。
Bug reports, containing crucial information such as the Observed Behavior (OB), the Expected Behavior (EB), and the Steps to Reproduce (S2R), can help developers localize and fix bugs efficiently. However, due to the increasing complexity of some bugs and the limited experience of some reporters, large numbers of bug reports miss this crucial information. Although machine learning (ML)-based and information retrieval (IR)-based approaches are proposed to detect and supplement the missing information in bug reports, the performance of these approaches depends heavily on the size and quality of bug report datasets.
DOI 原文 ·
@inproceedings{paperbot8435,
title = {ChatBR: Automated assessment and improvement of bug report quality using ChatGPT},
author = {Lili Bo and Wangjie Ji and Xiaobing Sun and Ting Zhang and Xiaoxue Wu and Ying Wei},
booktitle = {ASE},
year = {2024},
doi = {10.1145/3691620.3695518}
}