Detecting Patterns of Intimate Partner Violence Using Qualitative Analyses and Machine Learning Algorithms
Analyses 400 posts from women on intimate-partner-violence online forums using qualitative content analysis plus supervised text classification and unsupervised topic modelling. Classifies IPV subtypes and surfaces contextual patterns less visible in manual coding.
Publisher
Prevention Science (Springer)
Published
6 May 2026
Added
today
Key Findings
- Supervised models (Random Forest, neural networks) classified IPV subtypes at F1 .62-.85
- Coercive control emerged as a distinct, machine-detectable subtype alongside physical/sexual violence and psychological/emotional abuse
- Topic modelling surfaced relational, temporal, legal, and spatial context patterns beyond manual coding
Methodology Notes
Peer-reviewed, Prevention Science (6 May 2026), DOI 10.1007/s11121-026-01923-1. Mixed methods on 400 forum posts: qualitative content analysis + supervised classification + LDA topic modelling. Springer landing requires auth; title/authors/date/abstract verified via Crossref.
Sources
Authors
Ying Zhang, Jun Fang, Ambika Krishnakumar
Tags
Cite This
APA
Ying Zhang, Jun Fang, Ambika Krishnakumar (2026). Detecting Patterns of Intimate Partner Violence Using Qualitative Analyses and Machine Learning Algorithms. Prevention Science (Springer). https://doi.org/10.1007/s11121-026-01923-1
Related Insights
A Systematic Literature Review of the Use of Computational Text Analysis Methods in Intimate Partner Violence Research
Journal of Family Violence (Springer) · 21 Mar 2023
Classifying the Information Needs of Survivors of Domestic Violence in Online Health Communities Using Large Language Models: Prediction Model Development and Evaluation Study
Journal of Medical Internet Research (JMIR) · 12 May 2025
Large language models for psychosocial risk assessment: A multi-method evaluation across suicide, intimate partner violence, and substance misuse
PLOS Digital Health · 27 Apr 2026