Measuring Mental Health Stigma on Twitter
Conference Year
January 2020
Abstract
Major depression is a serious health issue afflicting hundreds of millions of people each year, with damaging physical and emotional effects exacerbated by intense stigma. In this project, we quantify trends in stigma surrounding mental illness using Twitter data. First, we show that the phrase “mental health” increased in popularity by a factor of 10 between 2013 and 2017. Additional words and phrases occurring in these messages reveal social trends responsible for the tremendous increase in collective attention. Second, we compile a list of negative labels commonly used in stigmatizing language, finding their popularity has largely decreased during this period. Finally, we identify depression diagnosis self-disclosure statements and report on their prevalence over time.
Primary Faculty Mentor Name
Christopher M. Danforth
Secondary Mentor Name
Peter Sheridan Dodds
Graduate Student Mentors
Thayer Alshaabi
Faculty/Staff Collaborators
Thayer Alshaabi, Peter Sheridan Dodds, Christopher M. Danforth
Status
Undergraduate
Student College
College of Engineering and Mathematical Sciences
Second Student College
Patrick Leahy Honors College
Program/Major
Data Science
Primary Research Category
Social Sciences
Secondary Research Category
Engineering & Physical Sciences
Tertiary Research Category
Health Sciences
Measuring Mental Health Stigma on Twitter
Major depression is a serious health issue afflicting hundreds of millions of people each year, with damaging physical and emotional effects exacerbated by intense stigma. In this project, we quantify trends in stigma surrounding mental illness using Twitter data. First, we show that the phrase “mental health” increased in popularity by a factor of 10 between 2013 and 2017. Additional words and phrases occurring in these messages reveal social trends responsible for the tremendous increase in collective attention. Second, we compile a list of negative labels commonly used in stigmatizing language, finding their popularity has largely decreased during this period. Finally, we identify depression diagnosis self-disclosure statements and report on their prevalence over time.