Abstract

Objective

Machine learning is used to understand and track influenza-related content on social media. Because these systems are used at scale, they have the potential to adversely impact the people they are built to help. In this study, we explore the biases of different machine learning methods for the specific task of detecting influenza-related content. We compare the performance of each model on tweets written in Standard American English (SAE) vs African American English (AAE).

Materials and Methods

Two influenza-related datasets are used to train 3 text classification models (support vector machine, convolutional neural network, bidirectional long short-term memory) with different feature sets. The datasets match real-world scenarios in which there is a large imbalance between SAE and AAE examples. The number of AAE examples for each class ranges from 2% to 5% in both datasets. We also evaluate each model's performance using a balanced dataset via undersampling.

Results

We find that all of the tested machine learning methods are biased on both datasets. The difference in false positive rates between SAE and AAE examples ranges from 0.01 to 0.35. The difference in the false negative rates ranges from 0.01 to 0.23. We also find that the neural network methods generally has more unfair results than the linear support vector machine on the chosen datasets.

Conclusions

The models that result in the most unfair predictions may vary from dataset to dataset. Practitioners should be aware of the potential harms related to applying machine learning to health-related social media data. At a minimum, we recommend evaluating fairness along with traditional evaluation metrics.

中文翻译：

---

使用机器学习在社交媒体上跟踪与流感相关的内容时存在种族偏见的风险

摘要

客观的

机器学习用于理解和跟踪社交媒体上与流感相关的内容。由于这些系统被大规模使用，它们有可能对它们旨在帮助的人产生不利影响。在这项研究中，我们探讨了不同机器学习方法对检测流感相关内容的特定任务的偏差。我们比较了每个模型在用标准美式英语 (SAE) 和非裔美式英语 (AAE) 编写的推文上的表现。

材料和方法

两个流感相关数据集用于训练具有不同特征集的 3 个文本分类模型（支持向量机、卷积神经网络、双向长短期记忆）。这些数据集与 SAE 和 AAE 示例之间存在很大不平衡的现实世界场景相匹配。在两个数据集中，每个类别的 AAE 示例的数量范围从 2% 到 5%。我们还通过欠采样使用平衡数据集评估每个模型的性能。

结果

我们发现所有经过测试的机器学习方法在两个数据集上都有偏差。SAE 和 AAE 示例之间的误报率差异在 0.01 到 0.35 之间。假阴性率的差异在 0.01 到 0.23 之间。我们还发现，在所选数据集上，神经网络方法通常比线性支持向量机具有更不公平的结果。

结论

导致最不公平预测的模型可能因数据集而异。从业者应该意识到将机器学习应用于与健康相关的社交媒体数据相关的潜在危害。至少，我们建议与传统评估指标一起评估公平性。