Measuring interpersonal firearm violence: natural language processing methods to address limitations in criminal charge data.

ABSTRACT

OBJECTIVE: Firearm violence constitutes a public health crisis in the United States, but comprehensive data infrastructure is lacking to study this problem. To address this challenge, we used natural language processing (NLP) to classify court record documents from alleged violent crimes as firearm-related or non-firearm-related. MATERIALS AND METHODS: We accessed and digitized court records from the state of Washington (n = 1472). Human review established a gold standard label for firearm involvement (yes/no). We developed a key term search and trained supervised machine learning classifiers for this labeling task. Results were evaluated in a held-out test set. RESULTS: The decision tree performed best (F1 score 0.82). The key term list had perfect recall (1.0) and a modest F1 score (0.65). DISCUSSION AND CONCLUSION: This case report highlights the accuracy, feasibility, and potential time-saved by using NLP to identify firearm involvement in alleged violent crimes based on digitized narratives from court documents.