一句话：构建 PR 评论数据集并评估机器学习模型，以自动识别软件开发交流中的性别歧视与厌女言论。
本文旨在为软件开发领域构建自动厌女/性别歧视识别工具。作者指出，男性主导的软件开发组织中，其他群体常在交流中遭遇性别歧视、厌女与歧视性（SMD）言论。方法上，作者基于关键词从 GitHub 挖掘 Pull Request 评论，并经人工验证得到 10,138 条评论数据集；随后使用十折交叉验证评估十种机器学习算法。最佳模型取得 80% 精确率、67.07% 召回率、72.5% F 值和 95.96% 准确率，表明自动识别 PR 评论中的 SMD 内容具有可行性，但召回率仍有提升空间。
Being extremely dominated by men, software development organizations lack diversity. People from other groups often encounter sexist, misogynistic, and discriminatory (SMD) speech during communication. To identify SMD contents, I aim to build an automatic misogyny identification (AMI) tool for the domain of software developers. On this goal, I built a dataset of 10,138 pull request comments mined from Github based on a keyword-based selection, followed by manual validation. Using ten-fold cross-validation, I evaluated ten machine learning algorithms for automatic identification. The best performing model achieved 80% precision, 67.07% recall, 72.5% f-score, and 95.96% accuracy.
DOI 原文 ·
@inproceedings{paperbot7164,
title = {Identifying Sexism and Misogyny in Pull Request Comments},
author = {Sayma Sultana},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3559515}
}