Academic Journal
Προβολή σε EDS

Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya.

Λεπτομέρειες βιβλιογραφικής εγγραφής
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
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=17582652&ISBN=&volume=29&issue=10&date=20261001&spage=e70214&pages=e70214&title=Journal of the International AIDS Society&atitle=Natural%20Language%20Processing%20Analysis%20of%20WhatsApp%20Messages%20to%20Identify%20Unrecognized%20HIV%20Prevention%20Needs%20Among%20Young%20Women%20in%20Kenya.&aulast=Haberer%20JE&id=DOI:10.1002/jia2.70214
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42834789
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Haberer+JE%22">Haberer JE</searchLink>; Center for Global Health, Massachusetts General Hospital, Boston, Massachusetts, USA.; Department of Medicine, Harvard Medical School, Boston, Massachusetts, USA.<br /><searchLink fieldCode="AU" term="%22Rono+B%22">Rono B</searchLink>; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya.<br /><searchLink fieldCode="AU" term="%22Ravi+R%22">Ravi R</searchLink>; North Carolina State University, Raleigh, North Carolina, USA.<br /><searchLink fieldCode="AU" term="%22Bagaria+V%22">Bagaria V</searchLink>; North Carolina State University, Raleigh, North Carolina, USA.<br /><searchLink fieldCode="AU" term="%22Shetty+S%22">Shetty S</searchLink>; North Carolina State University, Raleigh, North Carolina, USA.<br /><searchLink fieldCode="AU" term="%22Moparthi+S%22">Moparthi S</searchLink>; North Carolina State University, Raleigh, North Carolina, USA.<br /><searchLink fieldCode="AU" term="%22Oware+K%22">Oware K</searchLink>; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya.<br /><searchLink fieldCode="AU" term="%22Odoyo+JB%22">Odoyo JB</searchLink>; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya.<br /><searchLink fieldCode="AU" term="%22Garrison+L%22">Garrison L</searchLink>; Center for Global Health, Massachusetts General Hospital, Boston, Massachusetts, USA.<br /><searchLink fieldCode="AU" term="%22Rand+W%22">Rand W</searchLink>; North Carolina State University, Raleigh, North Carolina, USA.<br /><searchLink fieldCode="AU" term="%22Bukusi+EA%22">Bukusi EA</searchLink>; Centre for Microbiology Research, Kenya Medical Research Institute, Kisumu, Kenya.; Departments of Obstetrics and Gynecology and Global Health, University of Washington, Seattle, Washington, USA.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101478566%22">Journal of the International AIDS Society</searchLink> [J Int AIDS Soc] 2026 Oct; Vol. 29 (10), pp. e70214.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22John+Wiley+%26+Sons%2C+Inc%22">John Wiley & Sons, Inc </searchLink><i>Country of Publication: </i>Switzerland <i>NLM ID: </i>101478566 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1758-2652 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2217582652%22">17582652 </searchLink><i>NLM ISO Abbreviation: </i>J Int AIDS Soc <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 2017- : Hoboken, NJ : John Wiley & Sons, Inc<br /><i>Original Publication</i>: [London] : BioMed Central
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22HIV+Infections%22">HIV Infections*</searchLink>/<searchLink fieldCode="MM" term="%22HIV+Infections+prevention+%26+control%22">prevention & control</searchLink> <br /><searchLink fieldCode="MM" term="%22Natural+Language+Processing%22">Natural Language Processing*</searchLink> <br /><searchLink fieldCode="MM" term="%22Text+Messaging%22">Text Messaging*</searchLink> <br /><searchLink fieldCode="MM" term="%22Mobile+Applications%22">Mobile Applications*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Kenya%22">Kenya</searchLink> ; <searchLink fieldCode="MH" term="%22Adolescent%22">Adolescent</searchLink> ; <searchLink fieldCode="MH" term="%22Young+Adult%22">Young Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Surveys+and+Questionnaires%22">Surveys and Questionnaires</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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.<br />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).<br />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.<br />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.<br /> (© 2026 The Author(s). Journal of the International AIDS Society published by John Wiley & Sons Ltd on behalf of the International AIDS Society.)
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Bioethics. 2020 Nov;34(9):937-940. (PMID: <searchLink fieldCode="PM" term="%2233090500%22">33090500)</searchLink><br />Proceedings (IEEE Int Conf Bioinformatics Biomed). 2022 Dec;2022:3000-3007. (PMID: <searchLink fieldCode="PM" term="%2236818418%22">36818418)</searchLink><br />Artif Intell Med. 2021 Jul;117:102096. (PMID: <searchLink fieldCode="PM" term="%2234127235%22">34127235)</searchLink><br />AIDS Behav. 2026 Jan;30(1):253-262. (PMID: <searchLink fieldCode="PM" term="%2240826260%22">40826260)</searchLink><br />Curr HIV/AIDS Rep. 2022 Apr;19(2):154-165. (PMID: <searchLink fieldCode="PM" term="%2235147855%22">35147855)</searchLink><br />J Acquir Immune Defic Syndr. 2018 Feb 1;77(2):160-166. (PMID: <searchLink fieldCode="PM" term="%2229084046%22">29084046)</searchLink><br />Expert Syst Appl. 2021 Apr 1;167:114155. (PMID: <searchLink fieldCode="PM" term="%2233139966%22">33139966)</searchLink><br />Lancet. 2022 May 7;399(10337):1779-1789. (PMID: <searchLink fieldCode="PM" term="%2235378077%22">35378077)</searchLink><br />J Acquir Immune Defic Syndr. 2020 Oct 1;85(2):156-164. (PMID: <searchLink fieldCode="PM" term="%2232701820%22">32701820)</searchLink><br />JMIR Public Health Surveill. 2022 Apr 25;8(4):e32405. (PMID: <searchLink fieldCode="PM" term="%2235468092%22">35468092)</searchLink><br />PLoS One. 2020 Aug 26;15(8):e0235150. (PMID: <searchLink fieldCode="PM" term="%2232845882%22">32845882)</searchLink><br />J Int Assoc Provid AIDS Care. 2019 Jan-Dec;18:2325958219831011. (PMID: <searchLink fieldCode="PM" term="%2230776954%22">30776954)</searchLink><br />AIDS Behav. 2018 Jan;22(1):325-336. (PMID: <searchLink fieldCode="PM" term="%2228470458%22">28470458)</searchLink><br />Lancet HIV. 2023 Mar;10(3):e175-e185. (PMID: <searchLink fieldCode="PM" term="%2236702151%22">36702151)</searchLink><br />N Engl J Med. 2021 Aug 12;385(7):595-608. (PMID: <searchLink fieldCode="PM" term="%2234379922%22">34379922)</searchLink><br />JAMA. 2018 Mar 27;319(12):1261-1268. (PMID: <searchLink fieldCode="PM" term="%2229584848%22">29584848)</searchLink><br />J Med Internet Res. 2021 Apr 26;23(4):e22042. (PMID: <searchLink fieldCode="PM" term="%2233900200%22">33900200)</searchLink><br />J Med Internet Res. 2014 Dec 22;16(12):e290. (PMID: <searchLink fieldCode="PM" term="%2225533619%22">25533619)</searchLink><br />J Acquir Immune Defic Syndr. 2016 Jul 1;72(3):333-43. (PMID: <searchLink fieldCode="PM" term="%2226918545%22">26918545)</searchLink><br />PLoS One. 2021 Oct 14;16(10):e0258542. (PMID: <searchLink fieldCode="PM" term="%2234648589%22">34648589)</searchLink><br />J Int AIDS Soc. 2022 Jan;25(1):e25872. (PMID: <searchLink fieldCode="PM" term="%2235030296%22">35030296)</searchLink><br />AIDS. 2015 Jul 17;29(11):1277-85. (PMID: <searchLink fieldCode="PM" term="%2226103095%22">26103095)</searchLink>
– Name: GrantInfo
  Label: Grant Information
  Group: Grant
  Data: R21 MH132436 United States MH NIMH NIH HHS; R21MH132436 United States MH NIMH NIH HHS
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>HIV prevention; natural language processing; sub‐Saharan Africa; young women
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20261006 <i>Date Completed: </i>20261006 <i>Latest Revision: </i>20261008
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20261008
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13639533
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1002/jia2.70214
– Name: AN
  Label: PMID
  Group: ID
  Data: 42834789
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42834789
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/jia2.70214
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: e70214
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Kenya
        Type: general
      – SubjectFull: Adolescent
        Type: general
      – SubjectFull: Young Adult
        Type: general
      – SubjectFull: Surveys and Questionnaires
        Type: general
      – SubjectFull: HIV Infections prevention & control
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Text Messaging
        Type: general
      – SubjectFull: Mobile Applications
        Type: general
    Titles:
      – TitleFull: Natural Language Processing Analysis of WhatsApp Messages to Identify Unrecognized HIV Prevention Needs Among Young Women in Kenya.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Haberer JE
      – PersonEntity:
          Name:
            NameFull: Rono B
      – PersonEntity:
          Name:
            NameFull: Ravi R
      – PersonEntity:
          Name:
            NameFull: Bagaria V
      – PersonEntity:
          Name:
            NameFull: Shetty S
      – PersonEntity:
          Name:
            NameFull: Moparthi S
      – PersonEntity:
          Name:
            NameFull: Oware K
      – PersonEntity:
          Name:
            NameFull: Odoyo JB
      – PersonEntity:
          Name:
            NameFull: Garrison L
      – PersonEntity:
          Name:
            NameFull: Rand W
      – PersonEntity:
          Name:
            NameFull: Bukusi EA
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1758-2652
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Journal of the International AIDS Society
              Type: main
ResultId 1