Analyzing Framing through the Casts of Characters in the News

@inproceedings{Card2016AnalyzingFT,
  title={Analyzing Framing through the Casts of Characters in the News},
  author={Dallas Card and Justin H. Gross and Amber E. Boydstun and Noah A. Smith},
  booktitle={EMNLP},
  year={2016}
}
We present an unsupervised model for the discovery and clustering of latent “personas” (characterizations of entities). Our model simultaneously clusters documents featuring similar collections of personas. We evaluate this model on a collection of news articles about immigration, showing that personas help predict the coarse-grained framing annotations in the Media Frames Corpus. We also introduce automated model selection as a fair and robust form of feature evaluation.