Loading

Original Research Open Access

Digital Conversations about Severe Depression Symptoms Across Different Ethnic and Racial Groups: A Big-data, Machine Learning Analysis

  • 1University of Cincinnati, 2600 Clifton Ave, Cincinnati, OH 45221, USA
  • 2WARMI Mental Health, 7709 Cornell Rd, Cincinnati, OH 45242, USA
  • 3Universidad Del Norte, Puerto Colombia, Colombia, Área metropolitana de, Kilómetro 5, Vía Puerto Colombia, Barranquilla, Atlántico, Colombia
  • 4University of California, Irvine, CA 92697-5705, USA
  • 5Albert Einstein College of Medicine - PRIME. Bronx, New York, 1225 Morris Park Avenue, NY 10461, USA
  • 6Indiana University, 107 S. Indiana Avenue, Bloomington, IN 47405, USA
  • 7University of Alabama, 600 University Blvd. Suite C, Tuscaloosa, Alabama 35487, USA
+ Affiliations - Affiliations

Corresponding Author

Ruby Castilla-Puentes, castilrb@mail.uc.edu

Received Date: October 23, 2024

Accepted Date: January 03, 2025

Abstract

Background: Although studies have explored the use of technology and social media to help minorities suffering from depression, prior research has not thoroughly analyzed the racial and ethnic variation in the digital conversations related to symptoms of severe depression across racial/ethnic groups in the United States (U.S.).

Method: Machine-learning methods were used to extract open-source online conversations in the US from February 1, 2019, to November 1, 2020. The information included self-identified racial/ethnic groups: Hispanics, Non-Hispanic whites (NHw), African Americans and Asian Americans. Symptoms of Severe Depression were defined by the term “depression” and included at least two of the pre-determined severity adjectives described by the users in the conversation. Analyses were conducted for four domains: 1) Topics Generated, 2) Sentiments, 3) Mindset, and 4) Path to Treatment.

Results: A total of 1.3 million unique conversations referring to symptoms of severe depression posted during the selected period were analyzed. Conversations were most frequent among NHw 54%, Hispanics 21%, African Americans 20%, and 6% Asian Americans. Conversations were different across racial and ethnic groups: NHw talked more about diagnosis, making their conversations along the path to treatment more balanced out between the stages. They were more proactive than any other racial/ethnic groups. Depression was perceived as a more social phenomenon among African Americans. Asian Americans had the highest percentage of positive sentiment oriented toward the world and the future. Hispanics were less proactive, more negative, symptomatic, and less involved in treatment when compared with the conversations of other individuals of other racial/ethnic groups.

Conclusions: In conclusion, we have shown that conversations referring to symptoms of depression differs by race/ethnicity, and that these results highlight opportunities for culturally competent approaches to address areas amenable to change that could impact the ability of people to seek and receive mental health support. Future studies identifying ethnic/racial variations in severe depression symptoms may help to improve equity in mental health care.

Keywords

Artificial Intelligence, Severe, Depression, Symptoms, Ethnic, Racial

Author Information X