Facial expression-based human emotion recognition is a critical research area in psychology and medicine. State-of-the-art classification performance is only reached by end-to-end trained neural networks. Nevertheless, such black-box models lack transparency in their decision-making processes, prompting efforts to ascertain the rules that underlie classifiers' decisions. Analyzing single inputs alone fails to expose systematic learned biases. These biases can be characterized as facial properties summarizing abstract information like age or medical conditions. Therefore, understanding a model's prediction behavior requires an analysis rooted in causality along such selected properties. We demonstrate that up to 91.25% of classifier output behavior changes are statistically significant concerning basic properties. Among those are age, gender, and facial symmetry. Furthermore, the medical usage of surface electromyography significantly influences emotion prediction. We introduce a workflow to evaluate explicit properties and their impact. These insights might help medical professionals select and apply classifiers regarding their specialized data and properties.

翻译：基于面部表情的人类情绪识别是心理学和医学领域中的一个关键研究方向。目前，最先进的分类性能仅通过端到端训练的神经网络实现。然而，这类黑箱模型在其决策过程中缺乏透明度，促使人们努力确定分类器决策背后的规则。仅分析单一输入无法揭示系统性的学习偏差。这些偏差可被总结为抽象信息（如年龄或医疗状况）的面部属性。因此，理解模型的预测行为需要基于所选属性进行因果分析。我们证明，高达91.25%的分类器输出行为变化在基本属性（包括年龄、性别和面部对称性）上具有统计显著性。此外，表面肌电图在医疗中的使用显著影响情绪预测。我们引入了一套工作流程来评估显式属性及其影响。这些洞见可能帮助医疗专业人员根据其特定数据和属性选择和部署分类器。