TY - JOUR
T1 - An interpretable machine learning approach to multimodal stress detection in a simulated office environment
AU - Naegelin, Mara
AU - Weibel, Raphael P
AU - Kerr, Jasmine I
AU - Schinazi, Victor R
AU - La Marca, Roberto
AU - von Wangenheim, Florian
AU - Hoelscher, Christoph
AU - Ferrario, Andrea
N1 - Funding Information:
This study is part of a larger project and supported by the Donald C. Cooper Fonds via the ETH Zurich ( PS: 1-004675-000 ). We thank Dr. Stefan Wehrli and Giordano Giannoccolo from ETH Zurich’s Decision Science Laboratory for their assistance and Erika Meins, Sebastian Tillmanns, Marcus Zimmer, Anita Schärer, Hantao Zhao, Amray Schwabe, Caterina Bérubé, Yanick Lukic and Sabrina Trachsler for their supporting roles as research assistants and actors.
Publisher Copyright:
© 2023 The Author(s)
PY - 2023/3
Y1 - 2023/3
N2 - BACKGROUND AND OBJECTIVE: 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).METHODS: 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.RESULTS: 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.CONCLUSIONS: 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.
AB - BACKGROUND AND OBJECTIVE: 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).METHODS: 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.RESULTS: 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.CONCLUSIONS: 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.
UR - http://www.scopus.com/inward/record.url?scp=85147793634&partnerID=8YFLogxK
U2 - 10.1016/j.jbi.2023.104299
DO - 10.1016/j.jbi.2023.104299
M3 - Article
C2 - 36720332
SN - 0010-4809
VL - 139
SP - 104299
JO - Journal of Biomedical Informatics
JF - Journal of Biomedical Informatics
M1 - 104299
ER -
