Sensible Organizations

How do people behave in the workplace? While this is a simple question, it has been difficult to obtain precise behavioral data on this behavior in naturalistic settings. The Sensible Organizations aims to combine data from wearable sensing devices that can recognize conversations, speaking patterns, and physical movement (the Sociometric Badges) with electronic communication data, human observation data, and surveys to obtain a complete view of behavior in the workplace. We have used this data to highlight among other things the importance of informal interaction, the differences between e-mail and face-to-face communication, and the dynamic relationship between job satisfaction and face-to-face communication.

For more information, visit:

Modeling Corporate Epidemiology

Corporate responses to illness is currently an ad-hoc, subjective process that has little basis in data on how disease actually spreads at the workplace. Additionally, many studies have shown that productivity is not an individual factor but a social one: in any study on epidemic responses this social factor has to be taken into account. The barrier to addressing this problem has been the lack of data on the interaction and mobility patterns of people in the workplace. Using the data from the Sociometric Badges, we are able to simulate diseases spreading through face-to-face interactions with realistic epidemiological parameters. In this project we explore the trade offs between productivity and epidemic potential. We are able to take into account impacts on productivity that arise from social factors, such as interaction diversity and density, which studies that take an individual approach ignore. We also explore new organizational responses to diseases that take into account behavioral patterns that are associated with a more virulent disease spread. This is advantageous because it will allow companies to decide appropriate responses based on the organizational context of a disease outbreak.

A working paper on this topic can be found at:

Conversational Dynamics

Low-level conversation dynamics affects us in ways we often don't realize. Interrupting someone you're talking to signals your dominance, and speaking quickly and mimicking another person lead to higher conversational engagement. We have been testing how these dynamics correlate with outcomes in a variety of settings:

  • Nurse Handoffs
  • Salary Negotiations
  • Business Plan Pitches
  • Private Information Games
We have also created a program which changes the speaking style of an individual to investigate separate out content and presenation when evaulating outcomes. Publications on this topic can be found in my CV.