Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames

TL;DR

This paper introduces a semi-supervised, interpretable multi-view model that captures local event and actor information to improve news media frame classification, enhancing accuracy and transparency.

Contribution

A novel semi-supervised auto-encoding model that jointly learns local embeddings and document-level framing, offering improved performance and interpretability.

Findings

Outperforms previous frame prediction models

Leverages unlabeled data for better accuracy

Provides intuitive, interpretable embeddings

Abstract

Understanding how news media frame political issues is important due to its impact on public attitudes, yet hard to automate. Computational approaches have largely focused on classifying the frame of a full news article while framing signals are often subtle and local. Furthermore, automatic news analysis is a sensitive domain, and existing classifiers lack transparency in their predictions. This paper addresses both issues with a novel semi-supervised model, which jointly learns to embed local information about the events and related actors in a news article through an auto-encoding framework, and to leverage this signal for document-level frame classification. Our experiments show that: our model outperforms previous models of frame prediction; we can further improve performance with unlabeled training data leveraging the semi-supervised nature of our model; and the learnt event and actor embeddings intuitively corroborate the document-level predictions, providing a nuanced and interpretable article frame representation.