Peer-reviewed article
A Data Mining Approach to Clustering Cases of Violence Against Children in Indonesia
Agnes Irene Silitonga ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study used data mining to analyze violence against children across 38 Indonesian provinces. Researchers applied the K-Means Clustering algorithm to identify patterns in cases of physical, psychological, and sexual violence. Three clusters emerged: five provinces with high violence levels, 16 with moderate levels, and 17 with low levels. The findings are intended to support the development of geographically targeted child protection policies in Indonesia.
Key points
- Five provinces (North Sumatra, DKI Jakarta, West Java, Central Java, East Java) showed high levels of violence against children
- Clustering identified 16 provinces with moderate violence and 17 with low violence levels
- Data came from the Ministry of Women's Empowerment and Child Protection's official information system covering all 38 provinces
- Three types of violence were examined: physical, psychological, and sexual
- K-Means Clustering algorithm was used to find hidden patterns in large datasets
Limitations
This is a descriptive analysis that identifies geographic clusters of violence cases but does not evaluate any intervention or explain the causes of violence patterns. The document does not discuss the quality of case reporting, potential under-reporting, or the actual size and characteristics of the populations in each cluster.
Abstract
Violence against children in Indonesia remains a crucial issue that requires a data-driven approach for more targeted interventions. This study aims to cluster provinces in Indonesia based on the number of cases of violence and the types of violence committed, namely physical, psychological, and sexual violence. The method used in this study is the K-Means Clustering algorithm, an unsupervised learning technique in data mining that is able to find hidden patterns in large data sets. Data was obtained from the Ministry of Women's Empowerment and Child Protection's Gender and Child Information System (SIGA), which covers 38 provinces. The clustering results produced three main groups: a cluster with high levels of violence consisting of the provinces of North Sumatra, DKI Jakarta, West Java, Central Java, and East Java; a cluster with moderate levels of violence consisting of 16 provinces; and a cluster with low levels of violence covering 17 provinces. These findings are expected to form the basis for the development of evidence-based child protection policies geographically and thematically.