Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes
This addresses the issue of incomplete official data on hate crimes for policymakers and researchers, though it is incremental as it applies existing methods to a new domain.
The researchers tackled the problem of under-reported hate crimes in the US by using event extraction and multi-instance learning on local news articles to predict incidents, finding that hate crimes are under-reported compared to other crimes like homicide and kidnapping.
Official reports of hate crimes in the US are under-reported relative to the actual number of such incidents. Further, despite statistical approximations, there are no official reports from a large number of US cities regarding incidents of hate. Here, we first demonstrate that event extraction and multi-instance learning, applied to a corpus of local news articles, can be used to predict instances of hate crime. We then use the trained model to detect incidents of hate in cities for which the FBI lacks statistics. Lastly, we train models on predicting homicide and kidnapping, compare the predictions to FBI reports, and establish that incidents of hate are indeed under-reported, compared to other types of crimes, in local press.