UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening

Expresso Depresso




MAS: Media Arts and Sciences

Faculty Supervisor:

Cynthia Breazeal

Faculty email:


Apply by:

March 2nd, 2020 for Spring funding.


Felipe Moreno, pipemon@mit.edu

Project Description

Due to the widespread inaccessibility to mental health services in the world today and the stigma associated with mental illnesses, we propose a novel system to effectively detect depression markers and the severity of such with minimal intrusiveness and high reliability. The project's objective consists in creating a deep learning model to extract meaningful features associated to depression from interviews with participants, detecting the levels of depression in patients and understanding the fundamental markers in the prediction process.


- Proficiency with Python. - Machine learning familiarity at the level of 6.036/6.034. - Practical experience in machine learning or deep learning projects. - Experience in computer vision and/or signal processing is a plus. - Understanding of the Japanese language is a plus since the dataset contains interviews conducted with Japanese participants.