Data-driven identification of subtypes of intimate partner violence

Abstract

Intimate partner violence (IPV) is a complex problem with multiple layers of heterogeneity. We took a data-driven approach to characterize this heterogeneity. We integrated data from different studies, representing 640 individuals from various backgrounds. We used hierarchical clustering to systematically group cases in terms of their similarities according to violence variables. Results suggested that the cases can be clustered into 12 hierarchically organized subgroups, with verbal abuse and negotiation being the main discriminatory factors at higher levels. The presence of physical assault, injury, and sexual coercion was discriminative at lower levels of the hierarchy. Subgroups also exhibited significant differences in terms of relationship dynamics and individual factors. This study represents an attempt toward using integrative data analysis to understand the etiology of violence. These results can be useful in informing treatment efforts. The integrative data analysis framework we develop can also be applied to various other problems.

Artificial intelligence extracts key insights from legal documents to predict intimate partner femicide

“…Specifically, it was observed that high accuracy in differentiating these groups can be achieved by considering a comprehensive set of variables, including criminal history, prior sanctions, characteristics of violence against women perpetrated by their intimate partners, as well as the environmental and situational context in which this violence occurs. These results align with existing literature emphasizing the significance of considering a combination of variables for effective crime detection 54 – 59 .…”

Age-related injury patterns resulting from knife violence in an urban population

“…Third, although well-established, the cut-offs we used to compare age-related differences in injury patterns are arbitrary and may mask unrecognised within-group heterogeneity given the wide age range of the study cohort. Fourth, we did not perform a detailed analysis of the impact of gender on stab injury trends as this is beyond the scope of our study and had been investigated in detail previously 29 ; gender may have a confounding effect, although because of the small number of females in this cohort this is unlikely to alter the overall conclusions. However, females in our cohort had a higher median age and may have different injury characteristics, and therefore further study in this area is important.…”

Exploring Psychological Intimate Partner Violence Using Brief Expressive Writing Essays

“…It varies by intensity and frequency based on the impact of each behavior on the victim. NPIPV encompasses specific abuse tactics, including degradation, isolation, manipulation, restricting social interactions, controlling behaviors, gaslighting, and dominance (Doyle, 2020;Grace et al, 2020;Karakurt, 2021).…”

“…Further, individuals who report physical IPV victimization alongside NPIPV experience intensified versions of each IPV subtype (Hacialiefendioglu et al, 2021). If this conceptualization of IPV behaviors occurring on a continuum is supported, NPIPV may serve as an early identification of future more physically severe IPV victimization (Domenech del Rio & Garcia del Valle, 2016;Graham-Kevan & Archer, 2008).…”

“…There is often a disconnect in researching NPIPV as it may be challenging to recognize it as a form of abuse perpetrated by one's partner. Furthermore, individuals may struggle in their capacity to identify indirect behaviors (i.e., non-physical aggressive behaviors) as abuse but still experience the effects of fear, hopelessness, or humiliation (Chadambuka & Warria, 2018;Karakurt, 2021). Individuals can minimize their partners' perpetration by justifying or denying the behavior that occurs (Arriaga et al, 2018).…”