Algorithmic unfairness mitigation in student models: When fairer methods lead to unintended results
Algorithmic unfairness mitigation in student models: When fairer methods lead to unintended results
复制标题
学生模型中的算法不公平性缓解：当更公平的方法导致意想不到的结果时
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Nigel Bosch
中科院分区：
文献类型：
--
作者：
Frank Stinar;Nigel Bosch
系统性不公平的教育体系导致不同人口群体的学生学习水平不同，在人工智能驱动的教育背景下，这激发了减轻机器学习方法不公平性的工作。然而，缓解不公平的方法可能会给教室和学生带来意想不到的后果。我们在大型数据集（德克萨斯州学术准备评估 (STAAR) 结果数据）的背景下检查了预处理和后处理不公平缓解算法，以调查这些问题。我们使用不同的公平性定义跨多个机器学习模型评估了每种不公平性缓解算法。然后，我们评估了不公平缓解如何影响机器学习模型、不公平缓解方法和公平定义的不同组合的学生分类。平均而言，不公平缓解方法使公平性提高了 22%。在研究不公平缓解方法对预测的影响时，我们发现这些方法产生的模型能够并且确实对群体进行了过度概括。因此，此类模型做出的预测可能无法到达预期受众。我们讨论了人工智能驱动的干预措施和学生支持的影响。
Systematically unfair education systems lead to different levels of learning for students from different demographic groups, which, in the context of AI-driven education, has inspired work on mitigating unfairness in machine learning methods. However, unfairness mitigation methods may lead to unintended consequences for classrooms and students. We examined preprocessing and postprocessing unfairness mitigation algorithms in the context of a large dataset, the State of Texas Assessments of Academic Readiness (STAAR) outcome data, to investigate these issues. We evaluated each unfairness mitigation algorithm across multiple machine learning models using different definitions of fairness. We then evaluated how unfairness mitigation impacts classifications of students across different combinations of machine learning models, unfairness mitigation methods, and definitions of fairness. On average, unfairness mitigation methods led to a 22% improvement in fairness. When examining the impacts of unfairness mitigation methods on predictions, we found that these methods led to models that can and did overgeneralize groups. Consequently, predictions made by such models may not reach the intended au-diences. We discuss the implications for AI-driven interventions and student support.