一句话：控制实验表明，LGBTQ多元化配对在需求优先级排序中更一致地拒绝公平风险并减少公平性误判。
背景：公平与多样性在软件工程中日益受关注，尤其当AI与机器学习系统影响决策时。现有研究多从算法或数据层面讨论公平，对开发早期需求阶段及团队多样性如何影响公平决策了解有限。本文通过控制实验研究软件团队多样性如何影响需求优先级排序中的公平感知行为：27对软件工程学生（13对LGBTQ多元化配对、14对非多元化配对）对具有不同公平含义的用户故事进行优先级排序，并用描述统计与主题分析考察其态度、结果与理由。结果显示，两组总体认同公平原则，倾向支持促进平等对待的功能并拒绝公平风险功能；但LGBTQ多元化配对在拒绝公平风险故事上更一致，公平相关误优先级排序更少，其理由强调包容、非歧视与伦理责任，而非多元化配对更偏务实和目标导向。结论：公平应自软件开发早期阶段纳入考虑，团队多样性有助于在需求分析中识别和解释公平问题，促成更具反思性与包容性的决策。
Background: Fairness and diversity are receiving growing attention in software engineering, particularly as AI and machine learning systems increasingly influence decision-making processes. While fairness is often examined at the algorithmic or data level, there is limited understanding of how it is addressed during the early stages of software development. Moreover, little is known about how team diversity affects fairness-related decisions in software projects. Aims: This study investigates how diversity in software teams influences fairness-aware behavior during requirements prioritization. Method: A controlled experiment was conducted with 27 pairs of software engineering students, including 13 LGBTQ-diverse pairs and 14 non-diverse pairs. Each pair prioritized user stories with varying fairness implications. Descriptive statistics were used to analyze attitudes and prioritization outcomes, and thematic analysis was applied to examine the reasoning behind participants' decisions. Results: Both groups demonstrated general alignment with fairness principles, prioritizing features that promoted equitable treatment and rejecting those that posed fairness risks. However, LGBTQ-diverse pairs were more consistent in rejecting fairness-risking stories and made fewer fairness-related misprioritization errors. Their reasoning emphasized inclusion, non-discrimination, and ethical responsibility, whereas non-diverse pairs adopted a more pragmatic, goal-oriented perspective. Conclusions: The findings indicate that fairness should be considered from the earliest stages of software development. Team diversity can enhance the identification and interpretation of fairness issues during requirements analysis, fostering more reflective and inclusive decision-making.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2603-12406,
title = {Team Diversity Promotes Software Fairness: An Experiment on Fairness-Aware Requirements Prioritization},
author = {Cleyton Magalhães and Ronnie de Souza Santos and Bimpe Ayoola and Brody Stuart-Verner and Italo Santos},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805545}
}