Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks

AbstractThe trove of information contained in child maltreatment narratives represents an opportunity to strengthen the evidence base for policy reform in this area, yet it remains underutilized by researchers and policy makers. Current research into child maltreatment often involves the...

Full description

Saved in:
Bibliographic Details
Main Authors: Wilson Lukmanjaya, Tony Butler, Sarah Cox, Oscar Perez-Concha, Leah Bromfield, George Karystianis
Format: Article
Language:English
Published: JMIR Publications 2025-07-01
Series:JMIR Pediatrics and Parenting
Online Access:https://pediatrics.jmir.org/2025/1/e73579
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246210578186240
author Wilson Lukmanjaya
Tony Butler
Sarah Cox
Oscar Perez-Concha
Leah Bromfield
George Karystianis
author_facet Wilson Lukmanjaya
Tony Butler
Sarah Cox
Oscar Perez-Concha
Leah Bromfield
George Karystianis
author_sort Wilson Lukmanjaya
collection DOAJ
description AbstractThe trove of information contained in child maltreatment narratives represents an opportunity to strengthen the evidence base for policy reform in this area, yet it remains underutilized by researchers and policy makers. Current research into child maltreatment often involves the use of qualitative methodologies or structured survey data that are either too broad or not representative, thereby limiting the development of effective policy responses and intervention strategies. Artificial intelligence (AI) approaches such as large language models (AI models that understand and generate language) can analyze large volumes of child maltreatment narratives by extracting population-level insights on factors of interest such as mental health and treatment needs. However, when applying such methods, it is useful to have a framework on which to base approaches to the data. We propose a seven step framework: (1) data governance; (2) researcher vetting; (3) data deidentification; (4) data access; (5) feasibility testing of baseline methods; (6) large-scale implementation of black box algorithms; and (7) domain expert result validation for such exercises to ensure careful execution and limit the risk of privacy and security breaches, bias, and unreliable conclusions.
format Article
id doaj-art-e4d1b9d9431c402d97dc6db7b580aaae
institution Kabale University
issn 2561-6722
language English
publishDate 2025-07-01
publisher JMIR Publications
record_format Article
series JMIR Pediatrics and Parenting
spelling doaj-art-e4d1b9d9431c402d97dc6db7b580aaae2025-08-20T03:58:35ZengJMIR PublicationsJMIR Pediatrics and Parenting2561-67222025-07-018e73579e7357910.2196/73579Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable RisksWilson Lukmanjayahttp://orcid.org/0000-0002-7747-4648Tony Butlerhttp://orcid.org/0000-0002-2679-2769Sarah Coxhttp://orcid.org/0000-0003-0670-0692Oscar Perez-Conchahttp://orcid.org/0000-0002-8823-7090Leah Bromfieldhttp://orcid.org/0000-0002-4263-5878George Karystianishttp://orcid.org/0000-0003-3491-361X AbstractThe trove of information contained in child maltreatment narratives represents an opportunity to strengthen the evidence base for policy reform in this area, yet it remains underutilized by researchers and policy makers. Current research into child maltreatment often involves the use of qualitative methodologies or structured survey data that are either too broad or not representative, thereby limiting the development of effective policy responses and intervention strategies. Artificial intelligence (AI) approaches such as large language models (AI models that understand and generate language) can analyze large volumes of child maltreatment narratives by extracting population-level insights on factors of interest such as mental health and treatment needs. However, when applying such methods, it is useful to have a framework on which to base approaches to the data. We propose a seven step framework: (1) data governance; (2) researcher vetting; (3) data deidentification; (4) data access; (5) feasibility testing of baseline methods; (6) large-scale implementation of black box algorithms; and (7) domain expert result validation for such exercises to ensure careful execution and limit the risk of privacy and security breaches, bias, and unreliable conclusions.https://pediatrics.jmir.org/2025/1/e73579
spellingShingle Wilson Lukmanjaya
Tony Butler
Sarah Cox
Oscar Perez-Concha
Leah Bromfield
George Karystianis
Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
JMIR Pediatrics and Parenting
title Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
title_full Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
title_fullStr Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
title_full_unstemmed Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
title_short Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks
title_sort leveraging ai to investigate child maltreatment text narratives promising benefits and addressable risks
url https://pediatrics.jmir.org/2025/1/e73579
work_keys_str_mv AT wilsonlukmanjaya leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks
AT tonybutler leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks
AT sarahcox leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks
AT oscarperezconcha leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks
AT leahbromfield leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks
AT georgekarystianis leveragingaitoinvestigatechildmaltreatmenttextnarrativespromisingbenefitsandaddressablerisks