Stress modelling and prediction in presence of scarce data

[Display omitted] •Predicting stress levels from real world data collected from smartphones of 30 employees.•Addressing scarcity of labelled data through ensemble methods, semisupervised learning and transfer learning.•Improving classification accuracy of stress levels by 10–72% through the use of transfer learning. Stress at work is a significant occupational health concern. Recent studies have used various sensing modalities to model stress behaviour based on non-obtrusive data obtained from smartphones. However, when the data for a subject is scarce it becomes a challenge to obtain a good model. We propose an approach based on a combination of techniques: semi-supervised learning, ensemble methods and transfer learning to build a model of a subject with scarce data. Our approach is based on the comparison of decision trees to select the closest subject for knowledge transfer. We present a real-life, unconstrained study carried out with 30 employees within two organisations. The results show that using information (instances or model) from similar subjects can improve the accuracy of the subjects with scarce data. However, using transfer learning from dissimilar subjects can have a detrimental effect on the accuracy. Our proposed ensemble approach increased the accuracy by ≈10% to 71.58% compared to not using any transfer learning technique. In contrast to high precision but highly obtrusive sensors, using smartphone sensors for measuring daily behaviours allowed us to quantify behaviour changes, relevant to occupational stress. Furthermore, we have shown that use of transfer learning to select data from close models is a useful approach to improve accuracy in presence of scarce data.