Prediction of stress levels in the workplace using surrounding stress

• Published in: Information processing & management Vol. 59; no. 6; p. 103064
• Main Authors: Muñoz, Sergio, Iglesias, Carlos Á., Mayora, Oscar, Osmani, Venet
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2022
• Subjects: Ambient stress; Machine learning; Stress prediction; Surrounding stress; Workplace stress; Workplace stress; Ambient stress; Stress prediction; Surrounding stress; Machine learning
• ISSN: 0306-4573; 1873-5371
• DOI: 10.1016/j.ipm.2022.103064

Occupational stress has a significant adverse effect on workers’ well-being, productivity, and performance and is becoming a major concern for both individual companies and the overall economy. To reduce negative consequences, early detection of stress is a key factor. In response several stress prediction methods have been proposed, whose primary aim is to analyse physiological and behavioural data. However, evidence suggests that solutions based on physiological and behavioural data alone might be challenging when implemented in real-world settings. These solutions are sensitive to data problems arising from losses in signal quality or alterations in body responses, which are common in everyday activities. The contagious nature of stress and its sensitivity to the surroundings can be used to improve these methods. In this study, we sought to investigate automatic stress prediction using both surrounding stress data, which we define as close colleagues’ stress levels and the stress level history of the individuals. We introduce a real-life, unconstrained study conducted with 30 workers monitored over 8 weeks. Furthermore, we propose a method to investigate the effect of stress levels of close colleagues on the prediction of an individual’s stress levels. Our method is also validated on an external, independent dataset. Our results show that surrounding stress can be used to improve stress prediction in the workplace, where we achieve 80% of F-score in predicting individuals’ stress levels from the surrounding stress data in a multiclass stress classification. •An approach for stress prediction from surrounding stress-related data is proposed.•The approach uses the stress history of individuals and their close colleagues.•A real-life study with 30 employees monitored over a period of 8 weeks is presented.•The approach is validated on the own collected dataset and on a public dataset.•A statistical study to further analyze the effectiveness of our method is conducted.