Mental health monitoring through ‘selfie’ videos and social media tracking

Jiebo Luo and his colleagues at the University of Rochester announce they are developing a new way to monitor patients.

The article (here) says that currently, the team is working on a demo computer program that unobtrusively measures and analyses emotions from “selfie” videos when using social media. Currently, it can only define positive, neutral or negative, but in the future, they hope to “add extra sensitivity … by teaching it to further define a negative emotion as, for example, sadness or anger”.

This “would let users be more aware of their emotional fluctuations and make adjustments themselves.”

 Dawei Zhou, Vincent Silenzio, Yun Zhou, Glenn Currier, and Henry Kautz. “Tackling Mental Health by Integrating Unobtrusive Multimodal Sensing,”The 29th AAAI Conference on Artificial Intelligence (AAAI) takes place in Austin, Texas, from Jan. 25-30, 2015.