Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pastorino, Valeria, Sivakumar, Jasivan A., Moosavi, Nafise Sadat
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913150381588480
author Pastorino, Valeria
Sivakumar, Jasivan A.
Moosavi, Nafise Sadat
author_facet Pastorino, Valeria
Sivakumar, Jasivan A.
Moosavi, Nafise Sadat
contents The growing complexity and diversity of news coverage have made framing analysis a crucial yet challenging task in computational social science. Traditional approaches, including manual annotation and fine-tuned models, remain limited by high annotation costs, domain specificity, and inconsistent generalisation. Instruction-based large language models (LLMs) offer a promising alternative, yet their reliability for framing analysis remains insufficiently understood. In this paper, we conduct a systematic evaluation of several LLMs, including GPT-3.5/4, FLAN-T5, and Llama 3, across zero-shot, few-shot, and explanation-based prompting settings. Focusing on domain shift and inherent annotation ambiguity, we show that model performance is highly sensitive to prompt design and prone to systematic errors on ambiguous cases. Although LLMs, particularly GPT-4, exhibit stronger cross-domain generalisation, they also display systematic biases, most notably a tendency to conflate emotional language with framing. To enable principled evaluation under real-world topic diversity, we introduce a new dataset of out-of-domain news headlines covering diverse subjects. Finally, by analysing agreement patterns across multiple models on existing framing datasets, we demonstrate that cross-model consensus provides a useful signal for identifying contested annotations, offering a practical approach to dataset auditing in low-resource settings.
format Preprint
id arxiv_https___arxiv_org_abs_2402_11621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection
Pastorino, Valeria
Sivakumar, Jasivan A.
Moosavi, Nafise Sadat
Computation and Language
The growing complexity and diversity of news coverage have made framing analysis a crucial yet challenging task in computational social science. Traditional approaches, including manual annotation and fine-tuned models, remain limited by high annotation costs, domain specificity, and inconsistent generalisation. Instruction-based large language models (LLMs) offer a promising alternative, yet their reliability for framing analysis remains insufficiently understood. In this paper, we conduct a systematic evaluation of several LLMs, including GPT-3.5/4, FLAN-T5, and Llama 3, across zero-shot, few-shot, and explanation-based prompting settings. Focusing on domain shift and inherent annotation ambiguity, we show that model performance is highly sensitive to prompt design and prone to systematic errors on ambiguous cases. Although LLMs, particularly GPT-4, exhibit stronger cross-domain generalisation, they also display systematic biases, most notably a tendency to conflate emotional language with framing. To enable principled evaluation under real-world topic diversity, we introduce a new dataset of out-of-domain news headlines covering diverse subjects. Finally, by analysing agreement patterns across multiple models on existing framing datasets, we demonstrate that cross-model consensus provides a useful signal for identifying contested annotations, offering a practical approach to dataset auditing in low-resource settings.
title Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection
topic Computation and Language
url https://arxiv.org/abs/2402.11621