Naegelin Mara, Weibel Raphael P, Kerr Jasmine I, Schinazi Victor R, La Marca Roberto, von Wangenheim Florian, Hoelscher Christoph, Ferrario Andrea
Mobiliar Lab for Analytics at ETH Zurich, Department of Management, Economics, and Technology, ETH Zurich, Weinbergstrasse 56/58, Zurich, 8092, Switzerland; Chair of Technology Marketing, Department of Management, Economics, and Technology, ETH Zurich, Weinbergstrasse 56/58, Zurich, 8092, Switzerland.
Mobiliar Lab for Analytics at ETH Zurich, Department of Management, Economics, and Technology, ETH Zurich, Weinbergstrasse 56/58, Zurich, 8092, Switzerland; Chair of Technology Marketing, Department of Management, Economics, and Technology, ETH Zurich, Weinbergstrasse 56/58, Zurich, 8092, Switzerland.
J Biomed Inform. 2023 Mar;139:104299. doi: 10.1016/j.jbi.2023.104299. Epub 2023 Jan 30.
Work-related stress affects a large part of today's workforce and is known to have detrimental effects on physical and mental health. Continuous and unobtrusive stress detection may help prevent and reduce stress by providing personalised feedback and allowing for the development of just-in-time adaptive health interventions for stress management. Previous studies on stress detection in work environments have often struggled to adequately reflect real-world conditions in controlled laboratory experiments. To close this gap, in this paper, we present a machine learning methodology for stress detection based on multimodal data collected from unobtrusive sources in an experiment simulating a realistic group office environment (N=90).
We derive mouse, keyboard and heart rate variability features to detect three levels of perceived stress, valence and arousal with support vector machines, random forests and gradient boosting models using 10-fold cross-validation. We interpret the contributions of features to the model predictions with SHapley Additive exPlanations (SHAP) value plots.
The gradient boosting models based on mouse and keyboard features obtained the highest average F1 scores of 0.625, 0.631 and 0.775 for the multiclass prediction of perceived stress, arousal and valence, respectively. Our results indicate that the combination of mouse and keyboard features may be better suited to detect stress in office environments than heart rate variability, despite physiological signal-based stress detection being more established in theory and research. The analysis of SHAP value plots shows that specific mouse movement and typing behaviours may characterise different levels of stress.
Our study fills different methodological gaps in the research on the automated detection of stress in office environments, such as approximating real-life conditions in a laboratory and combining physiological and behavioural data sources. Implications for field studies on personalised, interpretable ML-based systems for the real-time detection of stress in real office environments are also discussed.
工作压力影响着当今很大一部分劳动力，且已知会对身心健康产生不利影响。持续且不引人注意的压力检测通过提供个性化反馈并允许开发用于压力管理的即时适应性健康干预措施，可能有助于预防和减轻压力。以往关于工作环境中压力检测的研究在受控实验室实验中往往难以充分反映现实世界的情况。为了弥补这一差距，在本文中，我们提出了一种基于多模态数据的机器学习方法，用于在模拟真实团队办公环境的实验（N = 90）中从不引人注意的来源收集数据来检测压力。
我们提取鼠标、键盘和心率变异性特征，使用支持向量机、随机森林和梯度提升模型，通过10折交叉验证来检测感知压力、效价和唤醒的三个水平。我们用SHapley加法解释（SHAP）值图来解释特征对模型预测的贡献。
基于鼠标和键盘特征的梯度提升模型在感知压力、唤醒和效价的多类预测中分别获得了最高平均F1分数，分别为0.625、0.631和0.775。我们的结果表明，尽管基于生理信号的压力检测在理论和研究中更为成熟，但鼠标和键盘特征的组合可能比心率变异性更适合检测办公环境中的压力。SHAP值图分析表明，特定的鼠标移动和打字行为可能表征不同程度的压力。
我们的研究填补了办公环境中压力自动检测研究中的不同方法学空白，例如在实验室中逼近现实生活条件以及结合生理和行为数据源。还讨论了对在实际办公环境中进行基于机器学习的个性化、可解释实时压力检测的现场研究的意义。
