Applying the Health Belief Model to Characterize Racial/Ethnic Differences in Digital Conversations Related to Depression Pre- and Mid-COVID-19: Descriptive Analysis
Bibliographic record
Abstract
BACKGROUND: The prevalence of depression in the United States is >3 times higher mid-COVID-19 versus prepandemic. Racial/ethnic differences in mindsets around depression and the potential impact of the COVID-19 pandemic are not well characterized. OBJECTIVE: This study aims to describe attitudes, mindsets, key drivers, and barriers related to depression pre- and mid-COVID-19 by race/ethnicity using digital conversations about depression mapped to health belief model (HBM) concepts. METHODS: Advanced search, data extraction, and artificial intelligence-powered tools were used to harvest, mine, and structure open-source digital conversations of US adults who engaged in conversations about depression pre- (February 1, 2019-February 29, 2020) and mid-COVID-19 pandemic (March 1, 2020-November 1, 2020) across the internet. Natural language processing, text analytics, and social data mining were used to categorize conversations that included a self-identifier into racial/ethnic groups. Conversations were mapped to HBM concepts (ie, perceived susceptibility, perceived severity, perceived benefits, perceived barriers, cues to action, and self-efficacy). Results are descriptive in nature. RESULTS: Of 2.9 and 1.3 million relevant digital conversations pre- and mid-COVID-19, race/ethnicity was determined among 1.8 million (62.2%) and 979,000 (75.3%) conversations, respectively. Pre-COVID-19, 1.3 million (72.1%) conversations about depression were analyzed among non-Hispanic Whites (NHW), 227,200 (12.6%) among Black Americans (BA), 189,200 (10.5%) among Hispanics, and 86,800 (4.8%) among Asian Americans (AS). Mid-COVID-19, a total of 736,100 (75.2%) conversations about depression were analyzed among NHW, 131,800 (13.5%) among BA, 78,300 (8.0%) among Hispanics, and 32,800 (3.3%) among AS. Conversations among all racial/ethnic groups had a negative tone, which increased pre- to mid-COVID-19; finding support from others was seen as a benefit among most groups. Hispanics had the highest rate of any racial/ethnic group of conversations showing an avoiding mindset toward their depression. Conversations related to external barriers to seeking treatment (eg, stigma, lack of support, and lack of resources) were generally more prevalent among Hispanics, BA, and AS than among NHW. Being able to benefit others and building a support system were key drivers to seeking help or treatment for all racial/ethnic groups. CONCLUSIONS: There were considerable racial/ethnic differences in drivers and barriers to seeking help and treatment for depression pre- and mid-COVID-19. As expected, COVID-19 has made conversations about depression more negative and with frequent discussions of barriers to seeking care. Applying concepts of the HBM to data on digital conversation about depression allowed organization of the most frequent themes by race/ethnicity. Individuals of all groups came online to discuss their depression. These data highlight opportunities for culturally competent and targeted approaches to addressing areas amenable to change that might impact the ability of people to ask for or receive mental health help, such as the constructs that comprise the HBM.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.020 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".