JMIR Publications

ABSTRACT

Background:

Police attend numerous domestic violence (DV) events each year, recording details of these events as both structured (coded) data and unstructured free text narratives. Abuse types (including physical, psychological, emotional and financial) along with any injuries sustained by victims are typically recorded in long descriptive narratives.

Objective:

In this paper we investigate if an automated text mining method can identify abuse types and any injuries sustained by DV victims in narratives contained in a large police data set from the New South Wales Police Force.

Methods:

We used a training set of 200 DV recorded events to design a knowledge-driven approach based on syntactical patterns in the text and then applied this to a large set of police reports.

Results:

Testing our approach on an evaluation set of 100 DV events returned a 90.2% and 85.0% precision for abuse type and victim injuries respectively. In a set of 492,393 DV reports, we found 71.32% (351,178) of events with mentions of the abuse type(s) and more than one third (35.97%; 177,117) contained victim injuries. ‘Emotional/verbal abuse’ (33.46%; 117,488) was the most common abuse type, followed by ‘punching’ (86,322; 24.58%) and ‘property damage’ (22.27%; 78,203). ‘Bruising’ was the most common form of injury sustained (29.03%; 51,455 events) with ‘cut/abrasion’ (28.93%; 51,284 events) and ‘red marks/signs’ (23.71%; 42,038 events) ranking second and third respectively.

Conclusions:

The results suggest that text mining can automatically extract information from police-recorded DV events that can support further public health research into domestic violence, such as examining the relationship between abuse types and victim injuries, between gender and abuse types and risk escalation for victims of DV. Potential also exists from this extracted information to be linked to information on mental health status.