Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 3:5:e48230.
doi: 10.2196/48230.

Messaging and Information in Mental Health Communication on Social Media: Computational and Quantitative Analysis

Rebecca K Ivic  1 , Amy Ritchart  1 , Shaheen Kanthawala  2 , Heather J Carmack  3
Affiliations

Messaging and Information in Mental Health Communication on Social Media: Computational and Quantitative Analysis

Rebecca K Ivic et al. JMIR Infodemiology. .

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.

Keywords: LIWC; Linguistic Inquiry and Word Count; computational analysis; health communication; large scale data; mental health; mental health organizations.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1.
Figure 1.. Concept map of the data.
Figure 2.
Figure 2.. Temporal engagement over time with mental health messages.
See this image and copyright information in PMC

References

    1. De Choudhury M, Gamon M, Counts S, Horvitz E. Predicting depression via social media. ICWSM. 2021;7(1):128–137. doi: 10.1609/icwsm.v7i1.14432. doi. - DOI
    1. Kostygina G, Tran H, Binns S, et al. Boosting health campaign reach and engagement through use of social media influencers and memes. Social Media + Society. 2020 Apr;6(2):205630512091247. doi: 10.1177/2056305120912475. doi. - DOI
    1. Angus D, Rintel S, Wiles J. Making sense of big text: a visual-first approach for analysing text data using Leximancer and Discursis. Int J Soc Res Methodol. 2013 May;16(3):261–267. doi: 10.1080/13645579.2013.774186. doi. - DOI
    1. Krishen AS, Petrescu M. The world of analytics: interdisciplinary, inclusive, insightful, and influential. J Market Anal. 2017 Mar;5(1):1–4. doi: 10.1057/s41270-017-0016-4. doi. - DOI
    1. Pill S, Harvey S, Hyndman B. Novel research approaches to gauge global teacher familiarity with game-based teaching in physical education: an exploratory #Twitter analysis. Asia Pac J Health Sport Phys Educ. 2017 May 4;8(2):161–178. doi: 10.1080/18377122.2017.1315953. doi. - DOI

LinkOut - more resources