Display options
Cite
Adrover C, Bodnar T, Huang Z, et al. Identifying Adverse Effects of HIV Drug Treatment and Associated Sentiments Using Twitter. JMIR Public Health Surveill. 2015;1(2):e7doi: 10.2196/publichealth.4488.
Adrover, C., Bodnar, T., Huang, Z., Telenti, A., & Salathé, M. (2015). Identifying Adverse Effects of HIV Drug Treatment and Associated Sentiments Using Twitter. JMIR public health and surveillance, 1(2), e7. https://doi.org/10.2196/publichealth.4488
Adrover, Cosme, et al. "Identifying Adverse Effects of HIV Drug Treatment and Associated Sentiments Using Twitter." JMIR public health and surveillance vol. 1,2 (2015): e7. doi: https://doi.org/10.2196/publichealth.4488
Adrover C, Bodnar T, Huang Z, Telenti A, Salathé M. Identifying Adverse Effects of HIV Drug Treatment and Associated Sentiments Using Twitter. JMIR Public Health Surveill. 2015 Jul 27;1(2):e7. doi: 10.2196/publichealth.4488. eCollection 2015. PMID: 27227141; PMCID: PMC4869211.
Copy Download .nbib Format: NLM
Share it on

JMIR Public Health Surveill. 2015 Jul 27;1(2):e7. doi: 10.2196/publichealth.4488. eCollection 2015.

Identifying Adverse Effects of HIV Drug Treatment and Associated Sentiments Using Twitter.

JMIR public health and surveillance

Cosme Adrover, Todd Bodnar, Zhuojie Huang, Amalio Telenti, Marcel Salathé

Affiliations

  1. Center for Infectious Disease DynamicsDepartment of BiologyPenn State UniversityUniversity Park, PAUnited States.
  2. J. Craig Venter InstituteLa Jolla, CAUnited States.

PMID: 27227141 PMCID: PMC4869211 DOI: 10.2196/publichealth.4488

Abstract

BACKGROUND: Social media platforms are increasingly seen as a source of data on a wide range of health issues. Twitter is of particular interest for public health surveillance because of its public nature. However, the very public nature of social media platforms such as Twitter may act as a barrier to public health surveillance, as people may be reluctant to publicly disclose information about their health. This is of particular concern in the context of diseases that are associated with a certain degree of stigma, such as HIV/AIDS.

OBJECTIVE: The objective of the study is to assess whether adverse effects of HIV drug treatment and associated sentiments can be determined using publicly available data from social media.

METHODS: We describe a combined approach of machine learning and crowdsourced human assessment to identify adverse effects of HIV drug treatment solely on individual reports posted publicly on Twitter. Starting from a large dataset of 40 million tweets collected over three years, we identify a very small subset (1642; 0.004%) of individual reports describing personal experiences with HIV drug treatment.

RESULTS: Despite the small size of the extracted final dataset, the summary representation of adverse effects attributed to specific drugs, or drug combinations, accurately captures well-recognized toxicities. In addition, the data allowed us to discriminate across specific drug compounds, to identify preferred drugs over time, and to capture novel events such as the availability of preexposure prophylaxis.

CONCLUSIONS: The effect of limited data sharing due to the public nature of the data can be partially offset by the large number of people sharing data in the first place, an observation that may play a key role in digital epidemiology in general.

Keywords: AIDS; HIV; Twitter; mTurk; mechanical Turk; pharmacovigilance

References

  1. Am Fam Physician. 2013 Oct 15;88(8):535-40 - PubMed
  2. J Acquir Immune Defic Syndr. 2015 Aug 1;69(4):422-9 - PubMed
  3. AIDS. 2003 Jul 4;17(10):1487-92 - PubMed
  4. PLoS One. 2013 Jul 24;8(7):e69305 - PubMed
  5. J Biomed Inform. 2015 Apr;54:202-12 - PubMed
  6. J Am Med Inform Assoc. 2013 May 1;20(3):404-8 - PubMed
  7. Lancet. 2001 Oct 20;358(9290):1322-7 - PubMed
  8. Drug Saf. 2014 May;37(5):343-50 - PubMed
  9. Prev Med. 2014 Jun;63:112-5 - PubMed
  10. N Engl J Med. 2013 Aug 1;369(5):401-4 - PubMed
  11. Curr Opin HIV AIDS. 2014 Jan;9(1):41-7 - PubMed
  12. PLoS One. 2010 Nov 29;5(11):e14118 - PubMed
  13. Crisis. 2014;35(1):51-9 - PubMed
  14. PLoS Comput Biol. 2012;8(7):e1002616 - PubMed
  15. PLoS Comput Biol. 2014 Apr 17;10(4):e1003581 - PubMed
  16. Science. 2014 Mar 14;343(6176):1203-5 - PubMed
  17. J Am Med Inform Assoc. 2014 Nov-Dec;21(6):1032-7 - PubMed
  18. JAMA. 2014 Jul 23-30;312(4):410-25 - PubMed
  19. J Med Internet Res. 2014 Jun 27;16(6):e157 - PubMed
  20. PLoS Comput Biol. 2011 Oct;7(10):e1002199 - PubMed
  21. Antivir Ther. 2007;12(8):1157-64 - PubMed
  22. Prev Med. 2014 Jun;63:109-11 - PubMed

Publication Types