Academic Journal
Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya.
| Τίτλος: | Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya. |
|---|---|
| Συγγραφείς: | Haberer JE; Center for Global Health, Massachusetts General Hospital, Boston, Massachusetts, USA.; Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA., Rono B; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya., Ravi R; North Carolina State University, Raleigh, North Carolina, USA., Bagaria V; North Carolina State University, Raleigh, North Carolina, USA., Shetty S; North Carolina State University, Raleigh, North Carolina, USA., Moparthi S; North Carolina State University, Raleigh, North Carolina, USA., Oware K; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya., Odoyo JB; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya., Garrison L; Center for Global Health, Massachusetts General Hospital, Boston, Massachusetts, USA., Rand W; North Carolina State University, Raleigh, North Carolina, USA., Bukusi EA; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya.; Departments of Obstetrics and Gynecology and Global Health, University of Washington, Seattle, Washington, USA. |
| Πηγή: | Journal of the International AIDS Society [J Int AIDS Soc] 2026 Oct; Vol. 29 (10), pp. e70214. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: John Wiley & Sons, Inc Country of Publication: Switzerland NLM ID: 101478566 Publication Model: Print Cited Medium: Internet ISSN: 1758-2652 (Electronic) Linking ISSN: 17582652 NLM ISO Abbreviation: J Int AIDS Soc Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2017- : Hoboken, NJ : John Wiley & Sons, Inc Original Publication: [London] : BioMed Central |
| Ιατρικοί όροι (MeSH): | HIV Infections*/prevention & control , Natural Language Processing* , Text Messaging* , Mobile Applications*, Humans ; Female ; Kenya ; Adolescent ; Young Adult ; Surveys and Questionnaires |
| Περίληψη: | Introduction: Identifying HIV prevention needs is challenging. Common approaches (e.g. public health campaigns, HIV risk scores) have limited sensitivity. Natural language processing techniques, such as topic modelling and computational linguistics, can extract meaning and subjective information from text. This study used these techniques with WhatsApp messages to identify unrecognized HIV prevention needs among young women in Kenya. Methods: Prior work established key ethical protections (e.g. privacy, confidentiality). Between July and December 2024, women (18-24 years) who used WhatsApp were enrolled from four clinical sites in Kisumu, Kenya. After completing a socio-demographic questionnaire, participants securely transferred all WhatsApp messages from the prior 6 months and provided anonymized relationship types (e.g. friend, sexual partner) for their 20 most frequent contacts. Data were de-identified, and only outgoing messages were retained; all photos and incoming messages were deleted. WhatsApp data were pre-processed using a downloaded large language model to translate Swahili and Dholuo to English and account for slang linguistic patterns. We explored multiple approaches to topic modelling in the WhatsApp data using latent Dirichlet allocation. Non-negative matrix factorization and uniform manifold approximation and projection allowed for comparison of participant word topics with the VOICE HIV risk score (range 0-8, 8 indicating high risk). Results: Of 413 eligible young women, 13 (3%) declined to provide WhatsApp data, and 22 had insufficient data for analysis. Participants had a mean age of 22 years and a VOICE risk score of 5.7. The remaining 378 women provided a median of 14 chats per individual. Participants most commonly chatted with friends (62.4%), followed by sexual partners (18.1%). The median VOICE risk score was 7 for women whose most messaged relationship was a sexual partner versus 5 for those messaging a friend most often. Topic models had differential correlation with the VOICE risk score that was most strongly positive (0.12) when indicating romance/affection and most strongly negative (-0.09) when describing faith/transactions. Dimensional analysis of linguistic similarity identified discrete participant populations with distinct VOICE risk scores. Conclusions: This study provides proof-of-concept that natural language processing of routine WhatsApp messages can yield meaningful individual-level information about HIV prevention needs. Future work should compare such findings with HIV incidence to optimally determine its ability to identify unrecognized HIV prevention needs, thus potentially expanding HIV prevention services to individuals not currently engaged in care. (© 2026 The Author(s). Journal of the International AIDS Society published by John Wiley & Sons Ltd on behalf of the International AIDS Society.) |
| References: | Bioethics. 2020 Nov;34(9):937-940. (PMID: 33090500) Proceedings (IEEE Int Conf Bioinformatics Biomed). 2022 Dec;2022:3000-3007. (PMID: 36818418) Artif Intell Med. 2021 Jul;117:102096. (PMID: 34127235) AIDS Behav. 2026 Jan;30(1):253-262. (PMID: 40826260) Curr HIV/AIDS Rep. 2022 Apr;19(2):154-165. (PMID: 35147855) J Acquir Immune Defic Syndr. 2018 Feb 1;77(2):160-166. (PMID: 29084046) Expert Syst Appl. 2021 Apr 1;167:114155. (PMID: 33139966) Lancet. 2022 May 7;399(10337):1779-1789. (PMID: 35378077) J Acquir Immune Defic Syndr. 2020 Oct 1;85(2):156-164. (PMID: 32701820) JMIR Public Health Surveill. 2022 Apr 25;8(4):e32405. (PMID: 35468092) PLoS One. 2020 Aug 26;15(8):e0235150. (PMID: 32845882) J Int Assoc Provid AIDS Care. 2019 Jan-Dec;18:2325958219831011. (PMID: 30776954) AIDS Behav. 2018 Jan;22(1):325-336. (PMID: 28470458) Lancet HIV. 2023 Mar;10(3):e175-e185. (PMID: 36702151) N Engl J Med. 2021 Aug 12;385(7):595-608. (PMID: 34379922) JAMA. 2018 Mar 27;319(12):1261-1268. (PMID: 29584848) J Med Internet Res. 2021 Apr 26;23(4):e22042. (PMID: 33900200) J Med Internet Res. 2014 Dec 22;16(12):e290. (PMID: 25533619) J Acquir Immune Defic Syndr. 2016 Jul 1;72(3):333-43. (PMID: 26918545) PLoS One. 2021 Oct 14;16(10):e0258542. (PMID: 34648589) J Int AIDS Soc. 2022 Jan;25(1):e25872. (PMID: 35030296) AIDS. 2015 Jul 17;29(11):1277-85. (PMID: 26103095) |
| Grant Information: | R21 MH132436 United States MH NIMH NIH HHS; R21MH132436 United States MH NIMH NIH HHS |
| Contributed Indexing: | Keywords: HIV prevention; natural language processing; sub‐Saharan Africa; young women |
| Entry Date(s): | Date Created: 20261006 Date Completed: 20261006 Latest Revision: 20261008 |
| Update Code: | 20261008 |
| PubMed Central ID: | PMC13639533 |
| DOI: | 10.1002/jia2.70214 |
| PMID: | 42834789 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!