An innovative device that employs infrared light to observe the effects of body language on social interactions has been developed by a research team including scientists from the University of Cambridge and Dartmouth College.
Since body language impacts various facets of the lives of humans - such as group projects, doctor-patient conversations, and job interviews - several people have attempted to explore them by using paper questionnaires, audio recordings, and video sessions.
However, since a majority of these methods require obtrusive devices, such as invasive cameras, they can be troublesome, inaccurate, and prejudiced on users.
To resolve this issue, the researchers developed the Protractor—a device that uses infrared light to gauge non-verbal behaviors that can possibly demonstrate the interaction of people in social settings.
Our system is a key departure from existing approaches. The ability to sense both body distance and relative angle with fine accuracy using only infrared light offers huge advantages and can deepen the understanding on how body language plays a role in social interactions.
Xia Zhou, Co-Lead Author & Assistant Professor of Computer Science at Dartmouth
The research, which is published in the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, will be presented at the UbiComp 2018 conference to be held from the October 8 to 12, 2018.
The Protractor, which looks like a wearable access badge worn with a clip or lanyard, operates on near-infrared light—a wavelength invisible to human eyes and generally used in TV remote controls. It monitors body language, including interpersonal distances and body angles.
“The ability to use invisible light to determine someone’s role and attitude in social settings has powerful implications for individuals and organizations that are concerned about how they communicate,” stated Cecilia Mascolo, professor of mobile systems at the University of Cambridge.
As a correction for when a user’s clothing or hand momentarily obscures the infrared light channel, the team designed algorithms that make use of inertial sensors to overcome the absence of light tracking results.
Furthermore, the light from each protractor tag was modulated to encode each light with a specific tag ID, in such a way that it was possible to recognize individuals wearing Protractor tags, added Zhao Tian, a doctoral candidate at Dartmouth. In addition, they matched the frequency of emitting light signals based on the exact context to reduce power consumption.
The Marshmallow Challenge
To investigate its effectiveness, the researchers used the Protractor tags to measure body language during a problem-solving group task called “The Marshmallow Challenge.”
For this task, four-member teams were given 18 minutes to construct a structure that could hold a marshmallow, with the help of a handful of spaghetti, string, and tape.
“We focused on two types of body language: the distances between users, and their relative body orientation,” stated Zhou. “These pairwise features can be aggregated as features to infer the instant task role of each team member, and the timeline, or stages, of the building process of the Marshmallow challenge.”
In the study which involved 64 participants, Protractor tags realized less than 6° error 95% of the time for gauging relative body orientation and a mean error of 1–2 inches in calculating distances between users.
The researchers used these measurements to identify stages in the building process with more than 93% accuracy and to evaluate the task role of each individual with nearly 85% accuracy.
Besides social research works, Protractor tags will also be used in other significant real-life settings.
They are capable of studying body language influenced by cultures in the present increasingly globalized workplaces, understanding team dynamics to attain higher creativity, and offering instantaneous feedback during interviews. “They (companies or institutions) can use Protractor results to study the correlation of our social interaction patterns with our personality, mental states, productivity, and cultural norms,” noted Zhou.
“They can use the results to possibly assess the effectiveness of team collaboration, and to train one’s engagement skills, which are essential for job interviews, doctor-patient interactions, sales training/orientation and more.”