{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:54:46Z","timestamp":1791273286903,"version":"4.1.0"},"reference-count":36,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T00:00:00Z","timestamp":1791244800000},"content-version":"vor","delay-in-days":5,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["R21MH132436"],"award-info":[{"award-number":["R21MH132436"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Int AIDS Soc."],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Prior work established key ethical protections (e.g. privacy, confidentiality). Between July and December 2024, women (18\u221224 years) who used WhatsApp were enrolled from four clinical sites in Kisumu, Kenya. After completing a socio\u2010demographic 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\u2010identified, and only outgoing messages were retained; all photos and incoming messages were deleted. WhatsApp data were pre\u2010processed 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\u2010negative matrix factorization and uniform manifold approximation and projection allowed for comparison of participant word topics with the VOICE HIV risk score (range 0\u20138, 8 indicating high risk).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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 (\u22120.09) when describing faith\/transactions. Dimensional analysis of linguistic similarity identified discrete participant populations with distinct VOICE risk scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study provides proof\u2010of\u2010concept that natural language processing of routine WhatsApp messages can yield meaningful individual\u2010level 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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/jia2.70214","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:37:27Z","timestamp":1791272247000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya"],"prefix":"10.1002","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-3190","authenticated-orcid":false,"given":"Jessica E.","family":"Haberer","sequence":"first","affiliation":[{"name":"Center for Global Health Massachusetts General Hospital  Boston Massachusetts USA"},{"name":"Department of Medicine Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Rono","sequence":"additional","affiliation":[{"name":"Centre for Microbiology Research Kenya Medical Research Institute  Kisumu Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1512-6448","authenticated-orcid":false,"given":"Rakesh","family":"Ravi","sequence":"additional","affiliation":[{"name":"North Carolina State University  Raleigh North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3605-4627","authenticated-orcid":false,"given":"Vinal","family":"Bagaria","sequence":"additional","affiliation":[{"name":"North Carolina State University  Raleigh North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9968-843X","authenticated-orcid":false,"given":"Sinchana","family":"Shetty","sequence":"additional","affiliation":[{"name":"North Carolina State University  Raleigh North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1263-5963","authenticated-orcid":false,"given":"Shanmukh","family":"Moparthi","sequence":"additional","affiliation":[{"name":"North Carolina State University  Raleigh North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Oware","sequence":"additional","affiliation":[{"name":"Centre for Microbiology Research Kenya Medical Research Institute  Kisumu Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josephine B.","family":"Odoyo","sequence":"additional","affiliation":[{"name":"Centre for Microbiology Research Kenya Medical Research Institute  Kisumu Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2384-4399","authenticated-orcid":false,"given":"Lindsey","family":"Garrison","sequence":"additional","affiliation":[{"name":"Center for Global Health Massachusetts General Hospital  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8294-1757","authenticated-orcid":false,"given":"William","family":"Rand","sequence":"additional","affiliation":[{"name":"North Carolina State University  Raleigh North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2031-2808","authenticated-orcid":false,"given":"Elizabeth A.","family":"Bukusi","sequence":"additional","affiliation":[{"name":"Centre for Microbiology Research Kenya Medical Research Institute  Kisumu Kenya"},{"name":"Departments of Obstetrics and Gynecology and Global Health University of Washington  Seattle Washington USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.1917"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2101016"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(22)00538\u20104"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/jia2.25872"},{"key":"e_1_2_12_6_1","unstructured":"Centers for Disease Control and Prevention HIV Risk and Prevention 2020 [cited 2022 April 27].https:\/\/www.cdc.gov\/hiv\/risk\/."},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1097\/QAD.0000000000000647"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/QAI.0000000000000974"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10461\u2010017\u20101785\u20107"},{"key":"e_1_2_12_10_1","unstructured":"Ministry of Health National AIDS and STI Control Program Pre\u2010Exposure Prophylaxis for the Prevention of HIV Infection: A Toolkit for Health Service Providers(2022).https:\/\/www.prepwatch.org\/wp\u2010content\/uploads\/2023\/04\/Kenya\u2010PrEP\u2010Framework.pdf. Assessed July 3 2026."},{"key":"e_1_2_12_11_1","doi-asserted-by":"crossref","DOI":"10.18356\/9789210019798","volume-title":"Danger: UNAIDS Global AIDS Update 2022","author":"UNAIDS","year":"2022"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2352\u20103018(22)00328\u20109"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1097\/QAI.0000000000002436"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11904\u2010022\u201000601\u20105"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0258542"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/2325958219831011"},{"key":"e_1_2_12_17_1","doi-asserted-by":"crossref","DOI":"10.1017\/9781108639286","volume-title":"Sentiment Analysis: Mining Opinions, Sentiments, and Emotions (Studies in Natural Language Processing)","author":"Liu B.","year":"2020"},{"key":"e_1_2_12_18_1","unstructured":"S.Adams How Tala Mobile Is Using Phone Data to Revolutionize Microfinance(2016) https:\/\/www.forbes.com\/sites\/forbestreptalks\/2016\/08\/29\/how\u2010tala\u2010mobile\u2010is\u2010using\u2010phone\u2010data\u2010to\u2010revolutionize\u2010microfinance\/?sh=436e55212a9f Accessed 25 Jan 2026."},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114155"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0235150"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1097\/QAI.0000000000001580"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.2196\/22042"},{"key":"e_1_2_12_23_1","unstructured":"R.Elliot Mobile Phone Penetration Throughout Sub\u2010Saharan Africa 2019[cited 2022 April 27].https:\/\/www.geopoll.com\/blog\/mobile\u2010phone\u2010penetration\u2010africa\/ Accessed 25 Jan 2026."},{"key":"e_1_2_12_24_1","unstructured":"GSM Association The Mobile Ecomony: Sub\u2010Saharan Africa(2022).https:\/\/www.gsma.com\/solutions\u2010and\u2010impact\/connectivity\u2010for\u2010good\/mobile\u2010economy\/wp\u2010content\/uploads\/2024\/05\/ME\u2010SSA\u20102022.pdf. Accessed: 25 January 2026."},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.3617"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/bioe.12823"},{"key":"e_1_2_12_27_1","volume-title":"Principles of Biomedical Ethics","author":"Beauchamp T.","year":"2012"},{"key":"e_1_2_12_28_1","volume-title":"Ethical Concerns and Suggested Mitigations Surrounding Access to and Use of SMS and Social Media Data in Sentiment Analysis for HIV Prevention Among Young Women in Western Kenya","author":"Odiera A.","year":"2025"},{"key":"e_1_2_12_29_1","unstructured":"The Data Protection Act Kenya(2019).https:\/\/new.kenyalaw.org\/akn\/ke\/act\/2019\/24\/eng%402019\u201011\u201015?utm. Accessed 24 Jan 2026."},{"key":"e_1_2_12_30_1","unstructured":"The Data Protection (General) Regulations(2021).https:\/\/new.kenyalaw.org\/akn\/ke\/act\/ln\/2021\/263\/eng@2022\u201001\u201014. Accessed 24 Jan 2026."},{"key":"e_1_2_12_31_1","doi-asserted-by":"crossref","unstructured":"J.YinandJ.Wang \u201cA Dirichlet Multinomial Mixture Model\u2010Based Approach for Short Text Clustering \u201d inProceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(Association for Computing Machinery 2014) 233\u2013242 https:\/\/doi.org\/10.1145\/2623330.2623715.","DOI":"10.1145\/2623330.2623715"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102096"},{"key":"e_1_2_12_33_1","unstructured":"W.Wang F.Wei L.Dong H.Bao N.Yang andM.Zhou \u201cMINILM: Deep Self\u2010Attention Distillation for Task\u2010Agnostic Compression of Pre\u2010Trained Transformers \u201d inCanada 34th Conference on Neural Information Processing Systems(2020)."},{"key":"e_1_2_12_34_1","unstructured":"L.McInnes J.Healy andJ.Melville UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction(2020)."},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10461\u2010025\u201004863\u2010z"},{"key":"e_1_2_12_36_1","first-page":"3000","article-title":"Using Twitter Data Analysis to Understand the Perceptions, Awareness, and Barriers to the Wide Use of Pre\u2010Exposure Prophylaxis in the United States","volume":"2022","author":"Erdengasileng A.","year":"2022","journal-title":"Proceedings for the IEEE International Conference on Bioinformatics and Biomedicine"},{"key":"e_1_2_12_37_1","doi-asserted-by":"publisher","DOI":"10.2196\/32405"}],"container-title":["Journal of the International AIDS Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jia2.70214","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jia2.70214","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jia2.70214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T07:37:32Z","timestamp":1791272252000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jia2.70214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/jia2.70214"],"URL":"https:\/\/doi.org\/10.1002\/jia2.70214","archive":["Portico"],"relation":{},"ISSN":["1758-2652","1758-2652"],"issn-type":[{"value":"1758-2652","type":"print"},{"value":"1758-2652","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"2026-01-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70214"}}