Back

Characterizing gun violence by time, day of the week, and holidays in six US cities 2015-2021

Klerman, E. B.; Affouf, M.; Robbins, R. B.; Iyer, J.; Masiakos, P.; Sacjs, C. A.

2022-12-30 public and global health
10.1101/2022.12.28.22283963 medRxiv
Show abstract

Developing interventions to prevent firearm-related violence and to address its consequences requires an improved understanding of when these violent events are most likely to occur. We explored gunshot events by time of day, day of week, and holiday/non-holiday in six major US cities. We utilized publicly available police department datasets that report the date and time of day of gunshot events from six major US cities. In these cities, shootings occurred most often at night and on holidays and weekends, with significant interaction effects. Primary prevention efforts should consider this differential risk.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.