LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma

TL;DR

This paper evaluates how large language models perform in targeted sentiment analysis of news headlines, examining the effects of prompt design and dataset subjectivity across languages, and assessing their uncertainty quantification capabilities.

Contribution

It provides a comprehensive comparison of LLMs and encoder models for TSA, analyzing prompt influence and dataset subjectivity, and evaluates LLMs' uncertainty calibration in a multilingual context.

Findings

LLMs outperform fine-tuned encoders on descriptive datasets

Calibration and F1-score improve with more prescriptive prompts

Optimal prompt level varies depending on the dataset and task

Abstract

News headlines often evoke sentiment by intentionally portraying entities in particular ways, making targeted sentiment analysis (TSA) of headlines a worthwhile but difficult task. Due to its subjectivity, creating TSA datasets can involve various annotation paradigms, from descriptive to prescriptive, either encouraging or limiting subjectivity. LLMs are a good fit for TSA due to their broad linguistic and world knowledge and in-context learning abilities, yet their performance depends on prompt design. In this paper, we compare the accuracy of state-of-the-art LLMs and fine-tuned encoder models for TSA of news headlines using descriptive and prescriptive datasets across several languages. Exploring the descriptive--prescriptive continuum, we analyze how performance is affected by prompt prescriptiveness, ranging from plain zero-shot to elaborate few-shot prompts. Finally, we evaluate the ability of LLMs to quantify uncertainty via calibration error and comparison to human label variation. We find that LLMs outperform fine-tuned encoders on descriptive datasets, while calibration and F1-score generally improve with increased prescriptiveness, yet the optimal level varies.