By Armita Adily, George Karystianis and Tony Butler

Police attend numerous family and domestic violence (FDV) related events each year and record details of these events as both structured data and unstructured free-text narratives. These descriptive narratives include information about the types of abuse (eg physical, emotional, financial) and the injuries sustained by victims. However, this information is not used in research. In this paper we demonstrate the application of an automated text mining method to identify abuse types and victim injuries in a large corpus of NSW Police Force FDV event narratives (492,393) recorded between January 2005 and December 2016. Specific types of abuse and victim injuries were identified in 71.3 percent and 35.9 percent of FDV event narratives respectively. The most commonly identified abuse types mentioned in the narratives were non-physical (55.4%). Our study supports the application of text mining for use in FDV research and monitoring.

Trends & issues in crime and criminal justice no. 630. Canberra: Australian Institute of Criminology. 2021. 12p.

By Armita Adily, George Karystianis and Tony Butler

In this paper, we describe the feasibility of using a text-mining method to generate new insights relating to family and domestic violence (FDV) from free-text police event narratives. Despite the rich descriptive content of the event narratives regarding the context and individuals involved in FDV events, the police narratives are untapped as a source of data to generate research evidence. We used text mining to automatically identify mentions of mental disorders for both persons of interest (POIs) and victims of FDV in 492,393 police event narratives created between January 2005 and December 2016. Mentions of mental disorders for both POIs and victims were identified in nearly 15.8 percent (77,995) of all FDV events. Of all events with mentions of mental disorder, 76.9 percent (60,032) and 16.4 percent (12,852) were related to either POIs or victims, respectively. The next step will be to use actual diagnoses from NSW Health records to determine concordance between the two data sources. We will also use text mining to extract information about the context of FDV events among key at-risk groups.

Trends & issues in crime and criminal justice no. 629. Canberra: Australian Institute of Criminology. 2021. 16p.