Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Media
This work addresses the challenge of understanding political discourse in news media for researchers and analysts, but it is incremental as it builds on existing frame analysis methods.
The paper tackles the problem of analyzing political polarization in news media by proposing a minimally-supervised approach to identify nuanced frames, breaking broad policy frames into fine-grained subframes for topics like immigration, gun-control, and abortion, and demonstrates their ability to capture ideological differences.
In this paper we suggest a minimally-supervised approach for identifying nuanced frames in news article coverage of politically divisive topics. We suggest to break the broad policy frames suggested by Boydstun et al., 2014 into fine-grained subframes which can capture differences in political ideology in a better way. We evaluate the suggested subframes and their embedding, learned using minimal supervision, over three topics, namely, immigration, gun-control and abortion. We demonstrate the ability of the subframes to capture ideological differences and analyze political discourse in news media.