Using the Pan American Health Organization Digital Conversational Agent to Educate the Public on Alcohol Use and Health: Preliminary Analysis
Open accessPublished version of a preprint
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Background: There is widespread misinformation about the effects of alcohol consumption on health, which was amplified during the COVID-19 pandemic through social media and internet channels. Chatbots and conversational agents became an important piece of the World Health Organization (WHO) response during the COVID-19 pandemic to quickly disseminate evidence-based information related to COVID-19 and tobacco to the public. The Pan American Health Organization (PAHO) seized the opportunity to develop a conversational agent to talk about alcohol-related topics and therefore complement traditional forms of health education that have been promoted in the past. Objective: This study aimed to develop and deploy a digital conversational agent to interact with an unlimited number of users anonymously, 24 hours a day, about alcohol topics, including ways to reduce risks from drinking, that is accessible in several languages, at no cost, and through various devices. Methods: The content development was based on the latest scientific evidence on the impacts of alcohol on health, social norms about drinking, and data from the WHO and PAHO. The agent itself was developed through a nonexclusive license agreement with a private company (Soul Machines) and included Google Digital Flow ES as the natural language processing software and Amazon Web Services for cloud services. Another company was contracted to program all the conversations, following the technical advice of PAHO staff. Results: The conversational agent was named Pahola, and it was deployed on November 19, 2021, through the PAHO website after a launch event with high publicity. No identifiable data were used and all interactions were anonymous, and therefore, this was not considered research with human subjects. Pahola speaks in English, Spanish, and Portuguese and interacts anonymously with a potentially infinite number of users through various digital devices. Users were required to accept the terms and conditions to enable access to their camera and microphone to interact with Pahola. Pahola attracted good attention from the media and reached 1.6 million people, leading to 236,000 clicks on its landing page, mostly through mobile devices. Only 1532 users had a conversation after clicking to talk to Pahola. The average time users spent talking to Pahola was 5 minutes. Major dropouts were observed in different steps of the conversation flow. Some questions asked by users were not anticipated during programming and could not be answered. Conclusions: Our findings showed several limitations to using a conversational agent for alcohol education to the general public. Improvements are needed to expand the content to make it more meaningful and engaging to the public. The potential of chatbots to educate the public on alcohol-related topics seems enormous but requires a long-term investment of resources and research to be useful and reach many more people.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Currently, the success of such digital health applications is mostly limited by technical constraints39 and limited acceptance by healthcare practitioners40.”
From The future landscape of large language models in medicine (2023) · cites this paper as [39]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Health Literacy: A Prescription to End Confusion
Committee on Health Literacy, Board on Neuroscience and Behavioral Health, & Institute of Medicine (2004) · doi:10.17226/10883 · Cited by 3,444
Degenhardt, L., Charlson, F., Ferrari, A., Santomauro, D., Erskine, H., Mantilla-Herrara, A., Whiteford, H., Leung, J., Naghavi, M., Griswold, M., et al. (2018) · The Lancet Psychiatry · doi:10.1016/s2215-0366(18)30337-7 · Cited by 1,572
Health literacy: a prescription to end confusion
(2005) · Choice Reviews Online · doi:10.5860/choice.42-4059 · Cited by 1,438
Moltu, C., Stefansen, J., Svisdahl, M., & Veseth, M. (2012) · Disability and Rehabilitation · doi:10.3109/09638288.2012.656792 · Cited by 1,247
Nadarzynski, T., Miles, O., Cowie, A., & Ridge, D. (2019) · DIGITAL HEALTH · doi:10.1177/2055207619871808 · Cited by 810 · cited 1×
“The use of smart conversational agents enables longer and customized conversations related to alcohol anytime people want and need, anonymously and confidentially [38].”
BackgroundShanghai declaration on promoting health in the 2030 Agenda for Sustainable Development
Organization, W. H. (2017) · Health Promotion International · doi:10.1093/heapro/daw103 · Cited by 473
Diederich, S., University of Göttingen, G., Brendel, A. B., TU Dresden, G., Morana, S., Saarland University, G., Kolbe, L., & University of Göttingen, G. (2022) · Journal of the Association for Information Systems · doi:10.17705/1jais.00724 · Cited by 313 · cited 1×
“Chatbots and conversational agents are a result of programmed algorithms that interact with users using natural language, either by text or voice, presenting capabilities to support natural language conversational interactions [30,31].”
BackgroundProbst, C., Kilian, C., Sanchez, S., Lange, S., & Rehm, J. (2020) · The Lancet Public Health · doi:10.1016/s2468-2667(20)30052-9 · Cited by 279
Probst, C., Roerecke, M., Behrendt, S., & Rehm, J. (2014) · International Journal of Epidemiology · doi:10.1093/ije/dyu043 · Cited by 270 · cited 1×
“Although these harms are widespread, socioeconomically disadvantaged populations are especially impacted [4,5], making alcohol a central driver of inequalities.”
BackgroundSocial Media and Medical Education in the Context of the COVID-19 Pandemic: Scoping Review
Katz, M., & Nandi, N. (2021) · JMIR Medical Education · doi:10.2196/25892 · Cited by 198 · cited 1×
“As a result, the existing low levels of health literacy [28] on alcohol and health, combined with the increased use of social media platforms such as Facebook, Twitter, Instagram, YouTube, WhatsApp, and podcasts [29], led to an unattainable situation requiring new and fast ways of communicating with the public using r…”
Background
Cited by
The future landscape of large language models in medicine
Clusmann, J., Kolbinger, F. R., Muti, H. S., Carrero, Z. I., Eckardt, J.-N., Laleh, N. G., Löffler, C. M. L., Schwarzkopf, S.-C., Unger, M., Veldhuizen, G. P., et al. (2023) · Communications Medicine · doi:10.1038/s43856-023-00370-1 · Cited by 1,045
“Currently, the success of such digital health applications is mostly limited by technical constraints 39 and limited acceptance by healthcare practitioners 40 .”
BackgroundTransforming healthcare with chatbots: Uses and applications—A scoping review
Barreda, M., Cantarero, D., Coca, D., Delgado, A., Lanza‐León, P., Lera, J., Montalbán, R., & Pérez, F. (2025) · Digital Health · doi:10.1177/20552076251319174 · Cited by 72
“Goldnadel et al. 21 and Peng et al. 38 showed promising results at this regard in educating the public on critical health issues, promoting preventive measures, and reducing the spread of misinformation.”
The application of artificial intelligence in health communication development: A scoping review
Weingott, S., & Parkinson, J. E. (2024) · Health Marketing Quarterly · doi:10.1080/07359683.2024.2422206 · Cited by 50
“…Brown et al., 2023; Chen et al., 2021; Cho et al., 2020; Eguchi et al., 2023; Entenberg et al., 2023; Kowatsch et al., 2021; Meheli et al., 2022; Monteiro et al., 2023; Okaniwa & Yoshida, 2022; Rughani et al., 2023; Sadasivam et al., 2016; Schm € alzle & Wilcox, 2022; Sinha et al., 2023;…”
Sohi, I., Shield, K. D., Rehm, J. T., & Monteiro, M. G. (2023) · Alcoholism Clinical and Experimental Research · doi:10.1111/acer.15175 · Cited by 30
Self-citationLópez-Ojeda, W., & Hurley, R. A. (2023) · Journal of Neuropsychiatry · doi:10.1176/appi.neuropsych.20230117 · Cited by 9
Chatbots and COVID-19: Taking Stock of the Lessons Learned
Arnold, V., Purnat, T. D., Marten, R., Pattison, A. B., & Gouda, H. (2024) · Journal of Medical Internet Research · doi:10.2196/54840 · Cited by 7
“…COVID-19 pandemic, national and subnational governments, as well as international health organizations such as the World Health Organization (WHO) [3,4] and the United States Centers for Disease Control and Prevention (CDC) [5], private companies, nongovernmental organizations, and researchers…”
Aguilar, K. N., Smith, M. L., Payne, S. C., Zhao, H., & Benden, M. E. (2024) · Applied Ergonomics · doi:10.1016/j.apergo.2024.104239 · Cited by 6
A Scoping Review of Large Language Model Chatbot Use for Alcohol and Other Drug Health Information
Harding, N., Bovopoulos, N., Caspi, D., Martin, C., McPhie, S., Bouadjenek, M. R., Aryal, S., & Hobbs, M. (2025) · Drug and Alcohol Review · doi:10.1111/dar.70068 · Cited by 3
A Bi-lingual chatbot implementation for pandemic response using the transformer-based approach
Atwine, M. T., Jjingo, D., Nsubuga, M., Sserunjogi, R., Mbabaali, I., Lujumba, I., David, B., Kintu, T. M., Galiwango, R. M., & Kebirungi, G. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001256 · Cited by 2
“…3) shows the final distribution: 375 English FAQ intents and 403 Luganda FAQ intents, with substantial overlap between the two language datasets. conversational agent [24] and consequently provide more accurate and contextually relevant responses which enhance the overall user experience [25–27].”
García, H. D., Hauser, M. P., & Zunino, S. M. R. (2025) · Revista Puertorriqueña de Psicología · Cited by 1
Development of Environmental Awareness as a Pedagogical Strategy for the Preservation of Ecosystems
Castillo, V. S. (2024) · Journal of Ecohumanism · doi:10.62754/joe.v3i1.6673 · Cited by 1
“Education is one of the main transformative axes in this regard (Monteiro et al., 2023).”
Model for the Creation and Decision-Making in Project Management Offices (PMO)
Ruiz, D. J. L., Acuña, L. A., Heredia-Rojas, B., Arabia, J. H., Pérez, P. Y. P., & Herrera, R. Y. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-83643-5_8
Ekonomi ve Yönetimde Yükselen Trendler
Şahin, Ö. U., & Kocaman, E. (2025) · doi:10.55094/holistence.263
The potential of online alcohol interventions for older adults
Conigrave, K. M. (2026) · The Lancet Public Health · doi:10.1016/s2468-2667(26)00076-9
Metadata
- Authors
- Monteiro, M. G., Pantani, D., Pinsky, I., & Hernandes Rocha, T. A.
- Affiliations
- World Health Organization Regional Office for the Americas (US)
- Corresponding author
- Monteiro, Maristela Goldnadel
- Venue
- JMIR Formative Research
- Publisher
- JMIR Publications Inc.
- Published
- 2023-04-06
- Volume
- 7
- Pages
- e43165
- ISSN
- 2561-326X (ISSN-L)
- PMC
- PMC10131863
- OpenAlex
- W4327660563
- Cited by
- 11
- References
- 33
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 3 · 2023: 3
- FWCI
- 2.97
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Formative Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Pan American Health Organization
- Topics
- Social Sciences › Health › Social Media in Health Education
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- chatbots, alcohol consumption, alcohol-related health, health education, Pan American Health Organization, digital health interventions, COVID-19 misinformation, user engagement, multilingual chatbot, natural language processing, chatbot limitations, public health communication
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
