Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Media

TL;DR

This paper introduces a minimally-supervised method to identify nuanced frames in news articles, capturing ideological differences more effectively across divisive political topics.

Contribution

It proposes breaking broad policy frames into fine-grained subframes and learns their embeddings with minimal supervision, improving analysis of political polarization.

Findings

Subframes effectively capture ideological differences.

Method applied successfully to immigration, gun-control, and abortion topics.

Demonstrates potential for nuanced political discourse analysis.

Abstract

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.