Child fatality is a significant public health problem. Nevertheless, an in-depth exploration of the circumstances surrounding the deaths of small children has not been a major research focus. To address the dearth of research, and to clarify inconsistencies, the present study analyzed the unstructured narrative text of N = 454 documents describing the details surrounding the deaths of children under the age of six years old. Machine Learning (ML) and Natural Language Processing (NLP) techniques were used to semantically and geographically map, extract and synthesize the unstructured text for the purpose of classification and identification of risk factors for fatal child maltreatment and victimization. In order to extract the most information possible while automating the data collection process, a Python routine was first implemented for the purpose of parsing and collecting HTML data derived from the Los Angeles County Office of the Coroner. The unstructured data were then mathematically transformed to reflect only the most important words in each report.

Using the resulting vectors as input data, a Self-Organizing Map (SOM) consisting of 12 x 8 dimensions was used to separate the document collection into identifiable clusters based on the similarity relationship between documents. The clusters were then linked to the spatial coordinates associated with each child fatality. The study has specific implications for understanding child death types and their shared modifiable risk factors as well as broader implications associated with how we collect, conceptualize and analyze data across different forms of interpersonal violence.