"When Can a Computer Improve Your Social Skills?"
This talk is a featured presentation of the National Science Foundation Research Experience for Undergraduates (NSF REU) on Computational Methods for Understanding Music, Media, and Minds and is open to all faculty, staff, students and community members.
Lunch sponsored by Goergen Institute for Data Science. Registration requested for adequate food.
Most people think someone is happy if he or she is smiling. Our research calls this intuition into question: in fact, most people are unable to differentiate between smiles elicited out of delight and out of frustration. What makes it so difficult?
Through a series of studies, we have constructed algorithms that automatically predict the underlying meanings of smiles—in some cases, better than humans. Applying these algorithmic insights, we can learn about deception, group dynamics, end-of-life communication between doctors and patients, negotiations, and even autism. How do we instantiate technical artefacts for a diverse set of applications using similar algorithmic intuitions? What are the underlying design considerations?
In this talk, I will share our insights from our findings on smiles that could lead to further insights into deception. I will also discuss how we used these insights to develop an application that provides automated feedback on public speaking to individuals—currently in use by ETS, ICICI Bank, and University of Rochester Career Services—as well as fosters improvements in group collaboration.
Ehsan Hoque is an Assistant Professor of Computer Science and the interim Director of the Goergen Institute for Data Science at the University of Rochester. He leads the Rochester Human-Computer Interaction (ROC HCI) group, which focuses on understanding and modelling the unwritten rules of human communication, with applications in business communication, health, and educational assessment technology.
Ehsan earned his Ph.D. from the MIT Media Lab in 2013, where his dissertation was highlighted by the MIT Museum as one of MIT’s most unconventional inventions. Ehsan has received an MIT TR35 award (2016), two Google Faculty Research Awards (2014, 2016), a commendation in Science News as one of ten early- to mid-career scientists to watch (2017), an Asago-Biggar (’92) Family Fellowship in Data Science (2017-2020), an NSF CAREER Award (2018), and four best-of-conference citations from IVA, UbiComp, FG, ACII. He is an associate editor of IEEE Transactions on Affective Computing, PACM IMWUT, and Digital Biomarkers.
Wednesday, June 20 at 12:00pm to 1:00pm
Wegmans Hall, Auditorium 1400
250 Hutchison Rd, Rochester, NY 14620