Characterizing Latent Perspectives of Media Houses Towards Public Figures

TL;DR

This paper introduces a zero-shot, generative approach using fine-tuned GPT-2 to characterize media house perspectives on public figures, aiming to better understand biases without relying on predefined labels.

Contribution

It presents a novel method of using twice fine-tuned GPT-2 for zero-shot characterization of entities from news articles, capturing subjective perspectives.

Findings

Encouraging results in generating characterizations compared to actual corpus data

Effective use of manual prompts for zero-shot entity characterization

Demonstrates potential for understanding media biases through generative models

Abstract

Media houses reporting on public figures, often come with their own biases stemming from their respective worldviews. A characterization of these underlying patterns helps us in better understanding and interpreting news stories. For this, we need diverse or subjective summarizations, which may not be amenable for classifying into predefined class labels. This work proposes a zero-shot approach for non-extractive or generative characterizations of person entities from a corpus using GPT-2. We use well-articulated articles from several well-known news media houses as a corpus to build a sound argument for this approach. First, we fine-tune a GPT-2 pre-trained language model with a corpus where specific person entities are characterized. Second, we further fine-tune this with demonstrations of person entity characterizations, created from a corpus of programmatically constructed characterizations. This twice fine-tuned model is primed with manual prompts consisting of entity names that were not previously encountered in the second fine-tuning, to generate a simple sentence about the entity. The results were encouraging, when compared against actual characterizations from the corpus.