Analyzing Themes, Sentiments, and Coping Strategies Regarding Online News Coverage of Depression in Hong Kong: Mixed Methods Study
Bibliographic record
Abstract
BACKGROUND: Depression, a highly prevalent global mental disorder, has prompted significant research concerning its association with social media use and its impact during Hong Kong's social unrest and COVID-19 pandemic. However, other mainstream media, specifically online news, has been largely overlooked. Despite extensive research conducted in countries, such as the United States, Australia, and Canada, to investigate the latent subthemes, sentiments, and coping strategies portrayed in depression-related news, the landscape in Hong Kong remains unexplored. OBJECTIVE: This study aims to uncover the latent subthemes presented in the online news coverage of depression in Hong Kong, examine the sentiment conveyed in the news, and assess whether coping strategies have been provided in the news for individuals experiencing depression. METHODS: This study used natural language processing (NLP) techniques, namely the latent Dirichlet allocation topic modeling and the Valence Aware Dictionary and Sentiment Reasoner (VADER) sentiment analysis, to fulfill the first and second objectives. Coping strategies were rigorously assessed and manually labeled with designated categories by content analysis. The online news was collected from February 2019 to May 2024 from Hong Kong mainstream news websites to examine the latest portrayal of depression, particularly during and after the social unrest and the COVID-19 pandemic. RESULTS: In total, 2435 news articles were retained for data analysis after the news screening process. A total of 7 subthemes were identified based on the topic modeling results. Societal system, law enforcement, global recession, lifestyle, leisure, health issues, and US politics were the latent subthemes. Moreover, the overall news exhibited a slightly positive sentiment. The correlations between the sentiment scores and the latent subthemes indicated that the societal system, law enforcement, health issues, and US politics revealed negative tendencies, while the remainder leaned toward a positive sentiment. The coping strategies for depression were substantially lacking; however, the categories emphasizing information on skills and resources and individual adjustment to cope with depression emerged as the priority focus. CONCLUSIONS: This pioneering study used a mixed methods approach where NLP was used to investigate latent subthemes and underlying sentiment in online news. Content analysis was also performed to examine available coping strategies. The findings of this research enhance our understanding of how depression is portrayed through online news in Hong Kong and the preferable coping strategies being used to mitigate depression. The potential impact on readers was discussed. Future research is encouraged to address the mentioned implications and limitations, with recommendations to apply advanced NLP techniques to a new mental health issue case or language.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".