Skip to main content
Peer-reviewed Authoritative

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.

Authors

Ying Zhang, Jun Fang, Ambika Krishnakumar

Tags

ipvcoercive-controlmachine-learningtext-classification

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