Entity Framing and Role Portrayal in the News

TL;DR

This paper introduces a multilingual, hierarchical dataset of news articles annotated for entity roles and portrayals, enabling advanced analysis of framing across languages and topics.

Contribution

It presents a novel, fine-grained taxonomy and a large annotated corpus for entity role portrayal in multilingual news, with evaluation of transformer and LLM models.

Findings

Transformer models achieve high accuracy in role classification.

Hierarchical zero-shot learning shows promise for cross-lingual role detection.

The dataset covers diverse languages and critical global issues.

Abstract

We introduce a novel multilingual hierarchical corpus annotated for entity framing and role portrayal in news articles. The dataset uses a unique taxonomy inspired by storytelling elements, comprising 22 fine-grained roles, or archetypes, nested within three main categories: protagonist, antagonist, and innocent. Each archetype is carefully defined, capturing nuanced portrayals of entities such as guardian, martyr, and underdog for protagonists; tyrant, deceiver, and bigot for antagonists; and victim, scapegoat, and exploited for innocents. The dataset includes 1,378 recent news articles in five languages (Bulgarian, English, Hindi, European Portuguese, and Russian) focusing on two critical domains of global significance: the Ukraine-Russia War and Climate Change. Over 5,800 entity mentions have been annotated with role labels. This dataset serves as a valuable resource for research into role portrayal and has broader implications for news analysis. We describe the characteristics of the dataset and the annotation process, and we report evaluation results on fine-tuned state-of-the-art multilingual transformers and hierarchical zero-shot learning using LLMs at the level of a document, a paragraph, and a sentence.