[论文解读] Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction

Nina Grgić-Hlača, Elissa M. Redmiles+2 more|arXiv (Cornell University)|Feb 26, 2018

Ethics and Social Impacts of AI参考文献 40被引用 71

一句话总结

本论文实证研究人们在使用 COMPAS 犯罪风险工具的特征时对公平性的感知，提出一个八属性框架，可从潜在特征属性以高准确度预测公平性判断。它揭示了超越歧视的多维不公平关切，以及受访者之间的显著分歧。

ABSTRACT

As algorithms are increasingly used to make important decisions that affect human lives, ranging from social benefit assignment to predicting risk of criminal recidivism, concerns have been raised about the fairness of algorithmic decision making. Most prior works on algorithmic fairness normatively prescribe how fair decisions ought to be made. In contrast, here, we descriptively survey users for how they perceive and reason about fairness in algorithmic decision making. A key contribution of this work is the framework we propose to understand why people perceive certain features as fair or unfair to be used in algorithms. Our framework identifies eight properties of features, such as relevance, volitionality and reliability, as latent considerations that inform people's moral judgments about the fairness of feature use in decision-making algorithms. We validate our framework through a series of scenario-based surveys with 576 people. We find that, based on a person's assessment of the eight latent properties of a feature in our exemplar scenario, we can accurately (> 85%) predict if the person will judge the use of the feature as fair. Our findings have important implications. At a high-level, we show that people's unfairness concerns are multi-dimensional and argue that future studies need to address unfairness concerns beyond discrimination. At a low-level, we find considerable disagreements in people's fairness judgments. We identify root causes of the disagreements, and note possible pathways to resolve them.

研究动机与目标

• 识别人们在算法决策中使用单个特征时如何判断其公平性。
• 提出一个潜在特征属性框架，影响公平性判断。
• 在刑事风险预测背景下，通过大规模调查（n=576）经验验证该框架。
• 分析公平性判断的共识与分歧及其原因。
• 讨论对设计更公平的算法决策系统的影响。

提出的方法

• 引入一个八属性潜在框架（可靠性、相关性、隐私、自主性、导致结果的原因、导致结果的恶性循环、导致结果差异的原因、由敏感群体身份引起）.
• 围绕 COMPAS 输入设计情景化调查，收集来自576名参与者的公平性判断。
• 进行预调查和正式调查，以评估潜在属性和公平性判断。
• 使用两个数据集（AMT 和 SSI）来评估可推广性与共识。
• 使用带有 L2 正则化的逻辑回归来从潜在属性评估预测公平性判断。

实验结果

研究问题

• RQ1 在决策场景中，人们在判断使用某一特征是否公平时，隐含使用了哪些潜在属性？
• RQ2 是否可以从对这些潜在属性的评估来预测公平性判断？
• RQ3 在不同特征及人群中，公平性判断的共识与分歧如何产生？
• RQ4 不公平关切是否超越歧视，扩展到其他特征属性？
• RQ5 这些发现对设计更公平的算法决策系统有何启示？

主要发现

• 大多数受访者认为大约一半的 COMPAS 特征在保释决策中不公平使用。
• 八个潜在属性能充分解释公平性判断，其中六个在分析中被显示为统计显著的预测变量。
• 使用一个简单分类器，从潜在属性评估中可以以高准确度（> 85%）预测公平性判断。
• 所识别的大多数公平性考虑与歧视无关，突显其他不公平关切。
• 在若干特征的公平性判断中存在相当大的分歧，这在很大程度上由对潜在属性，特别是因果属性的不同评估所驱动。
• 在潜在属性上训练的简单分类器能准确预测公平性判断，表明潜在属性可以被客观确定，而道德推理可通过调查获得。