The objective of this project is to automatically detect types of accountability in news articles when describing crimes such as shootings, using a dataset that was annotated with custom labels for this task. Analysis will be done to assess the given annotations, and build a classifier to automate this type of annotation for future research. Experiments will be conducted to compare various text representations and classification models. AutoML approaches will be used to tune parameters and optimize models. This project is in collaboration with Red Hen Lab, Dr. Glik from the UCLA school of public health.

Organization

Student

ajp

Mentors

  • Parker Sexton
  • Grace Kim-1
  • Deborah Glik
  • Francis Steen
close

2019