Physical violence against children and adolescents is more common than we think. In Argentina, 35 out of every 100 children and adolescents are physically punished and 7 out of every 100 are severely punished (UNICEF 2021).
The first key is that not all children and adolescents are exposed to the same level of risk. Those with disabilities or more than 5 years of age are almost twice as likely to suffer severe physical violence (own data based on UNICEF 2021).
The second key is that almost every mother or caregiver thinks that physical punishment is not necessary to get attention, raise or educate a child properly. Only a 2.6% thinks it is (UNICEF 2021).
So why is this means of discipline so common? The third key results from recent research indicating that child and adolescent characteristics (such as those mentioned above) and family factors are stronger predictors of physical punishment than those at the community or country level (Lansford et al. 2018, Ward et al. l 2021).
At family level, larger households with younger parents, stepfamilies, parents with low levels of education and caregivers who have been victims of child violence, face a higher probability of intrafamily violence. At community level, some risk factors are higher crime rates and greater residential mobility. At country level, higher rates of poverty, greater gender inequality and unemployment, increase the prevalence of violence.
Physical violence against children is a widespread phenomenon that we talk little about. The good news is that mothers, fathers and caregivers want to avoid it. From Abrazar we want to help them to choose positive parenting methods.
¹ The MICS survey conducted by UNICEF in 2019-20 asks mothers or caregivers about the methods used by the adults in the household to discipline children in the last month. Severe physical violence includes positive responses to 1) hitting or slapping a child on the face, head or ears, and 2) hitting or beating a child hard
Machine learning techniques and predictive analytics have enormous potential to prevent violence against children and adolescents. In this article we will tell you about two successful and promising experiences similar to Abrazar in the US and Chile. These programs use predictive analytics to reach the families that need help.
The Nurse-Family Partnership provides support to first-time moms in the US. They have trained nurses who regularly visit mothers starting early in the pregnancy and continuing through the child’s second birthday. Their results are amazing, they managed to reduce child abuse and neglect by 48%.
The Local Child Support Office (Oficina Local de la Niñez, OLN) in Chile is a free and voluntary service for children, adolescents and families at higher risk of vulnerability. To detect families at risk, they use an algorithm developed with administrative records. Their offices provide family therapy and access to government services. This program is being implemented in 12 communities on a pilot basis.
These experiences show how machine learning techniques and predictive analytics make it possible to reach the children and adolescents who need it most in a timely manner. These tools allow to conduct very effective programs which costs are prohibitively expensive to offer them universally.
Machine learning techniques can help state agencies improve the distribution of their resources, directing them to the families that need them most. This article summarizes local experiences in the USA where this technology was used for a) prioritizing cases to be investigated and b) meetings with families next to leave the protection system, and c) evaluating the provision of goods and services of state agencies that are part of the system.
The Florida Department of Children and Families (FDCF) and the Allegheny County in Pennsylvania (ACP) implemented models to predict risk of abuse and fatalities in their crisis lines and thus prioritizing cases for investigation (Cuccaro-Alamin et. al 2017).
The FDCF identified 14 risk factors associated with an increased risk of death, such as the child’s age, the child having been previously removed from his or her home, or the presence of physical or mental disability. The FDCF also developed an application for social workers to monitor risk factors and intervene in time to ensure the safety of children.
The ACP assigns a risk score indicating the likelihood that the child will be separated from the family and that the case will be referred back into the system within one year of the call. They are also considering using it to prioritize families’ invitations to the support programs.
The government of New York city used predictive models to identify risk factors among families who frequently interacted with protection services. Algorithms were applied to prioritize “exit meetings” among families who were about to exit the system and develop “risk cohorts” to adjust the performance measurement of agencies involved in providing services to these families.
The proposal does not intend to replace social workers’ professional opinion, but rather to provide them with another tool that allows them to assess risk, and to prevent children and families from not receiving the services they need due to an erroneous characterization of the risk level, which can perpetuate the situation of abuse or neglect.
In short, machine learning techniques and predictive analytics can help to better allocate the resources of the Protection System and thus protect more children and adolescents.