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
. 2023 Oct 10:25:e42960.
doi: 10.2196/42960.

Building a Chatbot in a Pandemic

Affiliations

Building a Chatbot in a Pandemic

Kimberly Rambaud et al. J Med Internet Res. .

Abstract

Easy access to evidence-based information on COVID-19 within an infodemic has been a challenging task. Chatbots have been introduced in times of emergency, when human resources are stretched thin and individuals need a user-centered resource. The World Health Organization Regional Office for Europe and UNICEF (United Nations Children's Fund) Europe and Central Asia came together to build a chatbot, HealthBuddy+, to assist country populations in the region to access accurate COVID-19 information in the local languages, adapted to the country context. Working in close collaboration with thematic technical experts, colleagues and counterparts at the country level allowed the project to be tailored to a diverse range of subtopics. To ensure that HealthBuddy+ was relevant and useful in countries across the region, the 2 regional offices worked closely with their counterparts in country offices, which were essential in partnering with national authorities, engaging communities, promoting the tool, and identifying the most relevant communication channels in which to embed HealthBuddy+. Over the past 2 years, the project has expanded from a web-based chatbot in 7 languages to a multistream, multifunction chatbot available in 16 regional languages, and HealthBuddy+ continues to expand and adjust to meet emerging health emergency needs.

Keywords: COVID-19; chatbots; conversational agent; digital health intervention; digital health tool; evidence-based communication channels; health communication; health promotion; online health information; user-centered.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: Both the lead and contributing authors at the World Health Organization (WHO) Regional Office for Europe and the United Nations Children's Fund (UNICEF) Europe and Central Asia Regional Office made up the HealthBuddy+ team at the regional level and contributed to collating shared challenges and experiences.

Figures

Figure 1
Figure 1
The technical architecture of HealthBuddy+. AI: artificial intelligence; API: application programming interface; CMS: content management system; HB+: HealthBuddy+.
Figure 2
Figure 2
Pipeline for content updates from translation to live. UNICEF: United Nations Children's Fund; WHO: World Health Organization.
Figure 3
Figure 3
Country example using trusted channels: Uzbekistan was the first partnering country to embed HealthBuddy+ into a popular messaging platform (Telegram), which it did in August 2021. The graph illustrates how incorporating the chatbot where citizens already communicate can increase the number of users overall.
Figure 4
Figure 4
Translation of left-hand panel: How to distinguish the symptoms of COVID-19 from the symptoms of the flu and other respiratory diseases? How can I find out what I have been infected with? Translation of right-hand panel: How long should I wait after full vaccination before planning a pregnancy?

References

    1. HealthBuddy: a new chatbot to engage with communities in Europe and central Asia on COVID-19. World Health Organization. [2022-04-29]. https://shorturl.at/aqBW1 .
    1. Amiri P, Karahanna E. Chatbot use cases in the Covid-19 public health response. J Am Med Inform Assoc. 2022 Apr 13;29(5):1000–1010. doi: 10.1093/jamia/ocac014. https://europepmc.org/abstract/MED/35137107 6523926 - DOI - PMC - PubMed
    1. Milne-Ives M, de Cock C, Lim E, Shehadeh MH, de Pennington N, Mole G, Normando E, Meinert E. The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review. J Med Internet Res. 2020 Oct 22;22(10):e20346. doi: 10.2196/20346. https://www.jmir.org/2020/10/e20346/ v22i10e20346 - DOI - PMC - PubMed
    1. Purnat TD, Vacca P, Czerniak C, Ball S, Burzo S, Zecchin T, Wright A, Bezbaruah S, Tanggol F, Dubé È, Labbé F, Dionne M, Lamichhane J, Mahajan A, Briand S, Nguyen T. Infodemic Signal Detection During the COVID-19 Pandemic: Development of a Methodology for Identifying Potential Information Voids in Online Conversations. JMIR Infodemiology. 2021 Jul 28;1(1):e30971. doi: 10.2196/30971. https://infodemiology.jmir.org/2021/1/e30971/ v1i1e30971 - DOI - PMC - PubMed
    1. Hawke A. U-Reporters mobilize to fight COVID-19. UNICEF Europe and Central Asia. [2022-06-14]. https://www.unicef.org/eca/stories/u-reporters-mobilize-fight-covid-19 .