Messaging and Information in Mental Health Communication on Social Media: Computational and Quantitative Analysis
Bibliographic record
Abstract
Background: Mental health organizations have the vital and difficult task of shaping public discourse and providing important information. Social media platforms such as X (formerly known as Twitter) serve as such communication channels, and analyzing organizational health information offers valuable insights into their guidance and linguistic patterns, which can enhance communication strategies for health campaigns and interventions. The findings inform strategies to enhance public engagement, trust, and the effectiveness of mental health messaging. Objective: This study examines the predominant themes and linguistic characteristics of messages from mental health organizations, focusing on how these messages' structure information, engage audiences, and contribute to public information and discourse on mental health. Methods: A computational content analysis was conducted to identify thematic clusters within messages from 17 unique mental health organizations, totaling 326,967 tweets and approximately 7.2 million words. In addition, Linguistic Inquiry and Word Count (LIWC) was used to analyze affective, social, and cognitive processes in messages with positive versus negative sentiment. Differences in sentiment were assessed using a Mann-Whitney U test. Results: The analysis revealed that organizations predominantly emphasize themes related to community, well-being, and workplace mental health. Sentiment analysis indicated significant differences in affect (P<.001), social processes (P<.001), and cognitive processing (P<.001) between positive and negative messages, with effect sizes that were small to medium. Notably, while messages frequently conveyed positive sentiment and social engagement, there was a lower emphasis on cognitive processing, suggesting that more complex discussions about mental health challenges may be underrepresented. Conclusions: Organizations use social media to promote engagement and support, often through positively valanced messages. Yet the limited emphasis on cognitive processing may indicate a gap in how organizations address more nuanced or complex mental health issues. Findings demonstrate the need for communication strategies that balance information with depth and clarity, ensuring that messages are trustworthy, actionable, and responsive to multiple mental health needs. By refining digital messaging strategies, organizations can enhance the effectiveness of health communication and improve engagement with mental health resources.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".