Home page

Using a list of common approved and regulated psychiatric drugs and a Twitter dataset of 300M posts from 30K individuals, we develop machine learning models to assess effects relating to mood, cognition, depression, anxiety, psychosis, and suicidal ideation. We observe that usage of specific drugs are associated with characteristic changes in an individual’s psychopathology. We situate these observations in the psychiatry literature, with a deeper analysis of pre-treatment cues that predict treatment outcomes, and post-treatment linguistic markers correlated with positive outcomes.

This project aimed to help self-driving vehicle drivers understand how the automation works in different driving conditions. Investment in educational resources can encourage the appropriate use of automated vehicle systems, and thus create a safe driving culture and environment. Instruction method and training content were investigated in this study. In-car interactive instructions were constructed to provide knowledge on underlying principles and feature usage.