AD
play_arrow

keyboard_arrow_right

Listeners:

Top listeners:

skip_previous skip_next
00:00 00:00
playlist_play chevron_left
volume_up
  • cover play_arrow

    HYFIN Connecting The Culture

  • play_arrow

    Rhythm Lab Radio Redefining the Urban Sound

  • play_arrow

    88Nine

  • play_arrow

    Discovering her past: Element uncovers her roots through African Ancestry DNA testing Tarik Moody

News

AI fails to detect depression in Black social media users, Penn Study finds

todayMarch 26, 2024

Background
share close
AD
AD
AI fails to detect depression in Black social media users, Penn Study finds

Artificial intelligence models designed to detect signs of depression in social media posts work far less effectively for Black users compared to white users, according to a new study from the University of Pennsylvania. The findings, published in the Proceedings of the National Academy of Sciences, highlight the need for AI to better account for racial differences in mental health screening.

Researchers from Penn Medicine and Penn Engineering analyzed Facebook posts from over 800 people, with equal representation of Black and white individuals who had reported depression. While the AI model performed strongly in identifying potential depression among white users based on their language, it was over three times less predictive for Black users.

“We were surprised that these language associations found in numerous prior studies didn’t apply across the board,” said senior author Sharath Chandra Guntuku, PhD, a researcher at Penn Medicine. “When thinking about mental health interventions, we should account for the differences among racial groups and how they may talk about depression. We cannot put everyone in the same bucket.”

The study found that factors like more frequent use of first-person pronouns by Black individuals, regardless of depression status, potentially confounded the AI model. Words related to self-deprecation and feeling like an outsider were linked to depression in white users but not Black users.

Lead author Sunny Rai, PhD, a postdoctoral researcher, noted the need for greater representation of diverse racial groups in studies to better understand varying expressions of depression. This could enable development of more precise predictive models and culturally-informed mental health support.

“AI-guided models that were developed using social media data can help in monitoring the prevalence of mental health disorders, especially depression, and their manifestations,” Rai said. “Such computational models hold promise in assisting policy-making as well as designing AI assistants that can provide affordable yet personalized healthcare options to citizens.”

Insights made through AI can also serve the education of professionals who help people manage depression.

“Understanding differences in how Black and white people with depression talk about themselves and their condition will be important when training psychotherapists who work across different communities,” said Lyle Ungar, PhD, a co-author on the study and professor of Computer and Information Science.

The authors plan to expand their research to examine how depression manifests across cultures beyond the U.S. As AI increasingly aids in mental health screening and treatment, ensuring it can serve all populations equitably will be critical. The Penn study illuminates key gaps that must be addressed to fulfill that promise.

AD

Written by: Tarik Moody

Rate it

Who we are

HYFIN is a media movement from Radio Milwaukee.

Milwaukee’s only Urban Alternative radio station features the full spectrum of Black music beyond R&B and Hip-Hop plus Milwaukee music. HYFIN connects the culture with the latest Black culture news, podcasts and more. Listen to best hip hop & R&B, dance, Afrobeats and more!

Listen

Our radio is always online!
Listen now completely free!
AD
AD
AD
AD
0%

Get your tickets now for just $10 in advance or $15 at the door and join us at 220 East Pittsburgh on May 10th.