We are delighted to announce that our innovative framing analysis tool is now publicly available in the LSS package. We performed analysis of the Russian media’s framing of street protests using a system developed in Python, but we ported the trained model to R to make it more accessible. We called it ‘dictionary’ earlier, but we decided to call it ‘model’ because it is a fitted Latent Semantic Scaling model. If you apply the model to your news stories, you can easily produce plots that are very similar to those in our papers. According to this model, a news article is framing street protests as “freedom of expression” when the score is high but protests as “social disorder” when score is low.
Continue reading “LSS model for protest framing analysis is available now”