Generalizability of Media Frames: Corpus creation and analysis across countries

TL;DR

This study examines whether the Media Frame Corpus (MFC), a framework for analyzing news frames, can be effectively applied across different cultural contexts by creating a Brazilian Portuguese dataset and evaluating model performance.

Contribution

The paper introduces FrameNews-PT, a new dataset of Brazilian news articles annotated with MFC frames, and assesses the cross-cultural generalizability of the MFC framework.

Findings

MFC frames are broadly applicable across cultures with minor revisions.

Some frames are rarely used, indicating cultural differences.

Fine-tuned and zero-shot models perform reasonably well on out-of-domain data.

Abstract

Frames capture aspects of an issue that are emphasized in a debate by interlocutors and can help us understand how political language conveys different perspectives and ultimately shapes people's opinions. The Media Frame Corpus (MFC) is the most commonly used framework with categories and detailed guidelines for operationalizing frames. It is, however, focused on a few salient U.S. news issues, making it unclear how well these frames can capture news issues in other cultural contexts. To explore this, we introduce FrameNews-PT, a dataset of Brazilian Portuguese news articles covering political and economic news and annotate it within the MFC framework. Through several annotation rounds, we evaluate the extent to which MFC frames generalize to the Brazilian debate issues. We further evaluate how fine-tuned and zero-shot models perform on out-of-domain data. Results show that the 15 MFC frames remain broadly applicable with minor revisions of the guidelines. However, some MFC frames are rarely used, and novel news issues are analyzed using general 'fall-back' frames. We conclude that cross-cultural frame use requires careful consideration.