Can we predict adolescents' involvement in family coflict using machine learning techniques?

What is it about?

One great concern about family violence is the role that children and adolescents play when these violent episodes take place. The question is: what makes them get involved in destructive family conflict? Because this clearly puts them into high risk. In fact, figures indicate that 90% of cases of violence against children and adolescents happen in their family home or other close environments. So, the objective of this study was to use machine learning techniques to predict adolescents' involvement in family conflict. We studied 251 adolescents (mean age = 15), of whom 84 were community adolescents and 167 were adolescents living in child protection services. We measured the conflict in their family, their emotional security in the family, their responses to analog interparental conflict (cognitive, emotional and behavioral responses) and sociodeographic variables (gender, age, etc). With a prediction accuracy of 65%, our results showed that adolescents in residential care are not at greater risk for involvement in family conflict compared to adolescents living with their families. Age and gender are not salient predictive variables. We could identify that responses to analog interparental conflict (IPC), adolescents’ emotional security, triangulation in IPC, and the presence of insults or blame during family disputes predict adolescents’ involvement in family conflict.

Featured Image

Photo by h heyerlein on Unsplash

Photo by h heyerlein on Unsplash

Why is it important?

This study has done several contributions. Two are methodological as 1. it has used machine learning techniques to make predictions in this field and 2. it has used analog coflict and an instrument to measure adolescents responses to analog conflict that were created in Spanish and ad hoc for this study. Another contribution is relevant for intervention and research as it has identified variables with a potential predictive capacity, among which we found adolescents' responses to analog conflict. These predictive variables are risk factors but also protection factors.

Perspectives