Email
jrwhitehill@wpi.edu
Office
100 Institute RD
Personal Website
Education
BS Computer Science Stanford University Departmental honors 2001
MS Computer Science University of the Western Cape Cum Laude 2007
PhD Computer Science University of California, San Diego 2012

My research interests are in applied machine learning, computer vision, data science and their applications to education, affective computing, and human behavior recognition. My work is highly interdisciplinary and frequently intersects cognitive science, psychology, and education. Before joining WPI, I was a research scientist at the Office of the Vice Provost for Advances in Learning at Harvard University. In 2012, I co-founded Emotient, a San Diego-based startup company for automatic emotion and facial expression recognition. I also love teaching and have lectured, mentored, and tutored students in the USA, South Africa, Rwanda, and Germany.

Research Interests
Machine learning
Affective computing
Intelligent tutoring systems
Computer vision

Scholarly Work

Who are they looking at? Automatic Eye Gaze Following for Classroom Observation Video Analysis. Aung, A., Ramakrishnan, A., and Whitehill, J. In Educational Data Mining, 2018.
Permutation-Invariant Consensus over Crowdsourced Labels. Giancola, M., Paffenroth, R., and Whitehill, J.. In Human Computation (HCOMP), 2018.
Harnessing Label Uncertainty to Improve Modeling: An Application to Student Engagement Recognition. Aung, A., and Whitehill, J. In IEEE Face & Gesture Recognition (FG), 2018.
Predicting When Teachers Look at Their Students in 1-on-1 Tutoring Sessions. Jiang, H., Dykstra, K., and Whitehill, J. In IEEE Face & Gesture Recognition (FG) Workshop on Human Behavior Understanding (HUB).
Beyond time-on-task: The relationship between spaced study and certification in moocs YR Miyamoto, CA Coleman, JJ Williams, J Whitehill, SO Nesterko, J Reich Available at SSRN 2547799
A stochastic optimal control perspective on affect-sensitive teaching JR Whitehill University of California, San Diego

News

SEE MORE NEWS ABOUT Jacob Richard Whitehill

Media Coverage

See All Media Coverage
Telegram.com
College Town: Nichols gets $2M anonymous gift

In its College Town section, The Telegram & Gazette featured how Jacob Whitehill, assistant professor of computer science, is collaborating with colleagues at the University of Colorado Boulder to explore how artificially intelligent (AI) teaching agents might help encourage more meaningful collaboration among students in school classrooms.

Forbes
Too Hot, Too Cold? Scientists Search For The Optimal Temperature For Learning

Forbes reported online about research led by Shichao Liu to study the optimal indoor conditions for learning. Liu, Jacob Whitehill and Steven Van Dessel received $299,991 develop technologies that detect and boost student engagement in lessons by controlling classroom temperature, ventilation, and lighting.