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.
Subject(s)
Firearms , Natural Language Processing , Humans , Firearms/legislation & jurisprudence , Washington , Violence , Machine Learning , Decision TreesABSTRACT
This paper analyzes ethnic segregation across the whole activity space-at place of residence, place of work, and during free-time. We focus on interethnic meeting potential during free-time, measured as copresence, and its relationship to copresence at place of residence and work. The study is based on cellphone data for a medium-sized linguistically divided European city (Tallinn, Estonia), where the Estonian majority and mainly Russian-speaking minority populations are of roughly equal size. The results show that both places of residence and work are segregated, while other activities occur in a far more integrated environment. Copresence during free-time is positively associated with copresence at place of residence and work, however, the relationship is very weak.