Our daily commute can tell a lot about our productivity at work, according to new research.
New research at Dartmouth College showcases the importance our commute can have on our workday. The findings show how certain behavior and psychological patterns we exhibit during commuting can be used to accurately predict job performance and employee satisfaction levels throughout the day.
The results are based on a year-long monitoring period of commuting workers prior to the outbreak of the COVID-19 pandemic.
Start of the day
“Your commute predicts your day,” said Andrew Campbell, the Albert Bradley 1915 Third Century Professor of computer science at Dartmouth, lead researcher and co-author of the study. “This research demonstrates that mobile sensing is capable of identifying how travel to and from the office affects individual workers.”
Data for the study was recorded through the smartphones and fitness trackers of 275 workers over a one-year monitoring period. The participants’ states were also recorded for 30 minutes before and after commuting. Most of these individuals (around 95%) drove to and from work, the team reports. Participants were provided with Garmin vivoSmart 3 activity tracker and a smartphone-based sensing app.
These devices were used to record a range of factors including the levels of physical activity, phone usage, heart rates, and stress levels. This body of data could be used to accurately predict workers’ productivity and satisfaction, the authors explain. The research could also help us to raise workers’ quality of life and help them be more productive.
“We were able to build machine learning models to accurately predict job performance,” said Subigya Nepal a PhD student at Dartmouth and lead author of the paper. “The key was being able to objectively assess commuting stress along with the physiological reaction to the commuting experience.”
Each worker’s day was assessed using ‘counterproductive work behavior’ and ‘organizational citizenship behavior’, two recognized criteria of job performance. The first is behavior that harms an organization’s overall efficiency, while the latter is beneficial. The baselines for each of these behaviors were set through regular, self-reported questionnaires sent in by participants.
“Compared to low performers, high performers display greater consistency in the time they arrive and leave work,” said Pino Audia, a professor of Management and Organizations at the Tuck School of Business, a senior scientist on the study team, and a co-author of the study. “This dramatically reduces the negative impacts of commuting variability and suggests that the secret to high performance may lie in sticking to better routines.”
Apart from this, high-performers tended to show more psychological markers of physical fitness and stress resilience. Low-performers showed higher levels of stress before, during, and after the commutes, and tended to use their phone more during commutes.
This aligns well with previous research on the topic, the team explains. Such research found that stress, anxiety, and frustration felt by individuals during their commute can reduce their efficiency at work, increase levels of counterproductive work behavior, and lower their engagement with organizational citizenship behavior. However, the current study is the first to link commuting data directly with workplace performance.
“The insights from this proof-of-concept study demonstrate that this is an important area of research for future of work,” said Campbell, co-director of Dartmouth’s DartNets Lab.
The small percentage of participants who engaged in active commuting — such as walking to work — showcased that such forms of commuting are typically associated with increased productivity during the day. Additionally, the study also found that people tended to spend more time commuting back home than they do going to work in the morning.
In the future, the team hopes that their findings can be used as a basis for new technology aimed at detecting and lowering commuter stress. Such interventions could include an app that offers suggestions for short stops, music, or podcasts aimed at improving a commuter’s emotional state.
The paper “Predicting Job Performance Using Mobile Sensing” has been published in the journal IEEE Pervasive Computing.