JMIR Publications

ABSTRACT

Background:

Biobehavioral rhythms are biological, behavioral, and psychosocial processes with repeating cycles. Abnormal rhythms have been linked to various health issues, such as sleep disorders, obesity, depression.

Objective:

The aim of this study is to identify links between productivity and biobehavioral rhythms modeled from passively collected mobile data streams.

Methods:

In this study, we utilized a multimodal mobile sensing dataset consisting of data collected from smartphones and Fitbits worn by 166 college students over a continuous period of 16 weeks. The participants reported their self-evaluated daily productivity score (ranging from 0-4) during week 1, 6, and 15. To analyze the data, we modeled cyclic human behavior patterns based on multimodal mobile sensing data gathered during weeks 1, 6, 15, and the adjacent weeks. Our methodology resulted in the creation of a rhythm model for each sensor feature. Additionally, we developed a correlation-based approach to identify connections between rhythm stability and high or low productivity levels. We also established a pipeline to extract essential rhythmic parameters from each sensor data stream, and employed these parameters to build machine learning models that can infer productivity levels.

Results:

Differences exist in the biobehavioral rhythms of high- and low-productive students, with those demonstrating greater rhythm stability also exhibiting higher productivity levels. Notably, a negative correlation (C = -0.16) was observed between productivity and the standard error of phase for the 24-hour period during week 1, with a higher SE indicative of lower rhythm stability. Our analysis additionally reveals that cyclic patterns of movement and sleep are predictive of productivity. The machine learning pipeline employed in this study, with an average duration of data collected from halls, achieves an F1 score of 0.83 when predicting low productivity, while the pipeline using the sum of duration of staying awake data achieves an F1 score of 0.8 for the same prediction.

Conclusions:

Modeling biobehavioral rhythms has the potential to quantify and forecast productivity. The findings have implications for building novel cyber-human systems that align with human’s biobehavioral rhythms to improve health, well-being, and work performance.