Presentation Title
The sentiment of depression on Twitter
Abstract
Major depression is a serious health issue afflicting hundreds of millions of people each year, with many going untreated due to the intense stigma surrounding mental illness. Using the Hedonometer, we analyze the sentiment of messages containing the word ‘depression’ posted to Twitter from 2008-2018. We then use a ‘white-box’ tool developed by our group to reveal the words most responsible for sentiment shifts. In particular, we identify specific dates on which sentiment deviates largely from the baseline in response to corresponding real-world events. The results offer insight into language use associated with depression on Twitter.
Primary Faculty Mentor Name
Chris Danforth
Secondary Mentor Name
Peter Dodds
Status
Undergraduate
Student College
College of Engineering and Mathematical Sciences
Program/Major
Data Science
Primary Research Category
Engineering & Physical Sciences
Secondary Research Category
Health Sciences
Tertiary Research Category
Social Sciences
The sentiment of depression on Twitter
Major depression is a serious health issue afflicting hundreds of millions of people each year, with many going untreated due to the intense stigma surrounding mental illness. Using the Hedonometer, we analyze the sentiment of messages containing the word ‘depression’ posted to Twitter from 2008-2018. We then use a ‘white-box’ tool developed by our group to reveal the words most responsible for sentiment shifts. In particular, we identify specific dates on which sentiment deviates largely from the baseline in response to corresponding real-world events. The results offer insight into language use associated with depression on Twitter.