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
. 2020 Oct 2;15(10):e0239304.
doi: 10.1371/journal.pone.0239304. eCollection 2020.

Use of social media big data as a novel HIV surveillance tool in South Africa

Alastair van Heerden  1   2 , Sean Young  3   4
Affiliations

Use of social media big data as a novel HIV surveillance tool in South Africa

Alastair van Heerden et al. PLoS One. .

Abstract

Sub-Saharan Africa has been heavily impacted by the HIV/AIDS epidemic. Social data (e.g., social media, internet search, wearable device, etc) show great promise assisting in public health and HIV surveillance. However, research on this topic has primarily focused in higher resource settings, such as the United States. It is especially important to study the prevalence and potential use of these data sources and tools in low- and middle-income countries (LMIC), such as Sub-Saharan Africa, which have been heavily impacted by the HIV epidemic, to determine the feasibility of using these technologies as surveillance and intervention tools. Accordingly, we 1) described the prevalence and characteristics of various social technologies within South Africa, 2) using Twitter, Instagram, and YouTube as a case study, analyzed the prevalence and patterns of social media use related to HIV risk in South Africa, and 3) mapped and statistically tested differences in HIV-related social media posts within regions of South Africa. Geocoded data were collected over a three-week period in 2018 (654,373 tweets, 90,410 Instagram posts and 14,133 YouTube videos with 1,121 comments). Of all tweets, 4,524 (0.7%) were found to related to HIV and AIDS. The percentage was similar for Instagram 95 (0.7%) but significantly lower for YouTube 18 (0.1%). We found regional differences in prevalence and use of social media related to HIV. We discuss the implication of data from these technologies in surveillance and interventions within South Africa and other LMICs.

PubMed Disclaimer

Conflict of interest statement

The authors have read the journal’s policy and have the following competing interests: SY received gift funding from Facebook and Intel, which was broadly used to support the Institute for Prediction Technology, of which SY is the director. This does not alter our adherence to PLOS ONE policies on sharing data and materials. There are no patents, products in development or marketed products associated with this research to declare.

Figures

Fig 1
Fig 1. Search strategy used to identify tweets originating in South Africa.
Fig 2
Fig 2. Subsection of the five kilometer point grid covering the entire extent of South Africa.
Fig 3
Fig 3. Map of South Africa showing distribution of Twitter, Instagram and YouTube social media post over a three-week period with road network overlaid.
Fig 4
Fig 4. Map of South Africa showing distribution of Twitter, Instagram and YouTube social media post related to HIV over a three-week period.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Ma Y, Wang Y, Yang J, Miao Y, Li W. Big Health Application System based on Health Internet of Things and Big Data. IEEE Access. 2017;5: 7885–7897. 10.1109/ACCESS.2016.2638449 - DOI
    1. Mehta N, Pandit A. Concurrence of big data analytics and healthcare: A systematic review. Int J Med Inform. 2018;114: 57–65. 10.1016/j.ijmedinf.2018.03.013 - DOI - PubMed
    1. Beam AL, Kohane IS. Big Data and Machine Learning in Health Care. JAMA. 2018;319: 1317 10.1001/jama.2017.18391 - DOI - PubMed
    1. Agarwal R, Dugas M, Gao G (Gordon), Kannan PK. Emerging technologies and analytics for a new era of value-centered marketing in healthcare. J Acad Mark Sci. 2020;48: 9–23. 10.1007/s11747-019-00692-4 - DOI
    1. Ishwarappa Anuradha J. A Brief Introduction on Big Data 5Vs Characteristics and Hadoop Technology. Procedia Comput Sci. 2015;48: 319–324. 10.1016/j.procs.2015.04.188 - DOI

Publication types

MeSH terms