Auditing for Discrimination in Algorithms Delivering Job Ads
Auditing for Discrimination in Algorithms Delivering Job Ads
复制标题
审核招聘广告算法中的歧视行为
DOI：
10.1145/3442381.3450077
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Heidemann, John
中科院分区：
文献类型：
--
作者：
Imana, Basileal;Korolova, Aleksandra;Heidemann, John
Facebook、谷歌和LinkedIn等广告平台通过其定向广告为广告商带来了价值。然而，多项研究表明，由于平台隐藏的算法优化，即使广告商没有要求，这些平台上的广告投放也会因性别或种族而倾斜。基于先前测量广告投放中的倾斜度的工作，我们开发了一种新的方法，用于对招聘广告投放中的歧视算法进行黑盒审计。我们的第一个贡献是确定由于受保护的类别（如性别或种族）而导致的广告投放偏差与由于目标受众中的人员资格差异而导致的偏差之间的区别。这种区别在美国法律中很重要，广告可以根据资格进行定位，而不是根据受保护的类别。其次，我们开发了一种审计方法，可以区分可由资格差异解释的偏斜与其他因素，例如广告平台的参与优化或在有偏见的数据上训练其算法。我们的方法控制工作资格，通过比较两个并发广告的广告交付类似的工作，但对公司与不同的事实上的性别分布的员工。我们描述了仔细的统计测试，建立证据的非资格的结果中的倾斜。第三，我们将我们提出的方法应用于两个突出的针对招聘广告的定向广告平台：Facebook和LinkedIn。我们确认了Facebook上广告投放的性别倾斜，并表明这不能通过资格差异来证明。我们在LinkedIn上没有发现广告投放的倾斜。最后，我们建议改进广告平台的做法，使其算法的外部审计更加可行和准确。
Ad platforms such as Facebook, Google and LinkedIn promise value for advertisers through their targeted advertising. However, multiple studies have shown that ad delivery on such platforms can be skewed by gender or race due to hidden algorithmic optimization by the platforms, even when not requested by the advertisers. Building on prior work measuring skew in ad delivery, we develop a new methodology for black-box auditing of algorithms for discrimination in the delivery of job advertisements. Our first contribution is to identify the distinction between skew in ad delivery due to protected categories such as gender or race, from skew due to differences in qualification among people in the targeted audience. This distinction is important in U.S. law, where ads may be targeted based on qualifications, but not on protected categories. Second, we develop an auditing methodology that distinguishes between skew explainable by differences in qualifications from other factors, such as the ad platform’s optimization for engagement or training its algorithms on biased data. Our method controls for job qualification by comparing ad delivery of two concurrent ads for similar jobs, but for a pair of companies with different de facto gender distributions of employees. We describe the careful statistical tests that establish evidence of non-qualification skew in the results. Third, we apply our proposed methodology to two prominent targeted advertising platforms for job ads: Facebook and LinkedIn. We confirm skew by gender in ad delivery on Facebook, and show that it cannot be justified by differences in qualifications. We fail to find skew in ad delivery on LinkedIn. Finally, we suggest improvements to ad platform practices that could make external auditing of their algorithms in the public interest more feasible and accurate.
登录
查看更多内容
构建和审核公平算法：候选人筛选案例研究
DOI：
10.1145/3442188.3445928
发表时间：
2021
期刊：
Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
影响因子：
--
作者：
Christo Wilson;A. Ghosh;Shan Jiang;A. Mislove;Lewis Baker;Janelle Szary;Kelly Trindel;Frida Polli
通讯作者：
Frida Polli
“看不到颜色”的算法：测量相似和特殊广告受众的偏差
DOI：
10.1145/3514094.3534135
发表时间：
2022
期刊：
and Society
影响因子：
--
作者：
Sapiezynski, Piotr;Ghosh, Avijit;Kaplan, Levi;Rieke, Aaron;Mislove, Alan
通讯作者：
Mislove, Alan
Sunlight：具有统计可信度的大规模细粒度目标检测
DOI：
10.1145/2810103.2813614
发表时间：
2015
期刊：
Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security
影响因子：
--
作者：
Mathias Lécuyer;Riley Spahn;Yannis Spiliopolous;A. Chaintreau;Roxana Geambasu;Daniel J. Hsu
通讯作者：
Daniel J. Hsu
Facebook 的广告平台：新的攻击媒介和干预的必要性
DOI：
--
发表时间：
2018
期刊：
arXiv.org
影响因子：
--
作者：
Irfan Faizullabhoy;A. Korolova
通讯作者：
A. Korolova
影响因子：
--
作者：
A. Cohen;Kobbi Nissim
通讯作者：
Kobbi Nissim